Daily Papers

Large vision-language models (VLMs) often rely on familiar semantic priors, but existing evaluations do not cleanly separate perception failures from rule-mapping failures. We study this behavior as semantic fixation: preserving a default interpretation even when the prompt specifies an alternative, equally valid mapping. To isolate this effect, we introduce VLM-Fix, a controlled benchmark over four abstract strategy games that evaluates identical terminal board states under paired standard and inverse rule formulations. Across 14 open and closed VLMs, accuracy consistently favors standard rules, revealing a robust semantic-fixation gap. Prompt interventions support this mechanism: neutral alias prompts substantially narrow the inverse-rule gap, while semantically loaded aliases reopen it. Post-training is strongly rule-aligned: training on one rule improves same-rule transfer but hurts opposite-rule transfer, while joint-rule training improves broader transfer. To test external validity beyond synthetic games, we evaluate analogous defamiliarization interventions on VLMBias and observe the same qualitative pattern. Finally, late-layer activation steering partially recovers degraded performance, indicating that semantic-fixation errors are at least partly editable in late representations. Project page, code, and dataset available at https://maveryn.github.io/vlm-fix/.

Despite high benchmark scores, Large Language Models (LLMs) often fail simple problem, raising a critical question: Do LLMs learn mathematical principles or merely memorize patterns? Rather than designing increasingly complex benchmarks like recent works, we investigate this using elementary two-integer addition (0 to 2^{64}), probing two core properties: commutativity (A+B=B+A) and compositional generalization (via isomorphic symbolic mappings, e.g., 7 rightarrow y). While state-of-the-art LLMs achieve 73.8-99.8\% accuracy on numerical addition, performance collapses to leq7.5\% under symbolic mapping, indicating failure to generalize learned rules. Non-monotonic performance scaling with digit count and frequent commutativity violations (over 1,700 cases of A+B neq B+A) further support this. Explicitly providing addition rules degrades performance by 81.2\% on average, while self-explanation maintains baseline accuracy, suggesting LLM arithmetic processing is misaligned with human-defined principles. Our findings indicate current LLMs rely on memory pattern over genuine rule learning, highlighting architectural limitations and the need for new approaches to achieve true mathematical reasoning.

Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce , a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.

Large datasets have become commonplace in NLP research. However, the increased emphasis on data quantity has made it challenging to assess the quality of data. We introduce Data Maps---a model-based tool to characterize and diagnose datasets. We leverage a largely ignored source of information: the behavior of the model on individual instances during training (training dynamics) for building data maps. This yields two intuitive measures for each example---the model's confidence in the true class, and the variability of this confidence across epochs---obtained in a single run of training. Experiments across four datasets show that these model-dependent measures reveal three distinct regions in the data map, each with pronounced characteristics. First, our data maps show the presence of "ambiguous" regions with respect to the model, which contribute the most towards out-of-distribution generalization. Second, the most populous regions in the data are "easy to learn" for the model, and play an important role in model optimization. Finally, data maps uncover a region with instances that the model finds "hard to learn"; these often correspond to labeling errors. Our results indicate that a shift in focus from quantity to quality of data could lead to robust models and improved out-of-distribution generalization.

We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback overexisting rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0

Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively evaluating against full-scale knowledge bases is computationally prohibitive, especially for closed-weight models. We propose stochastic error ascent (SEA), a scalable and efficient framework for discovering knowledge deficiencies (errors) in closed-weight LLMs under a strict query budget. Rather than naively probing all knowledge candidates, SEA formulates error discovery as a stochastic optimization process: it iteratively retrieves new high-error candidates by leveraging the semantic similarity to previously observed failures. To further enhance search efficiency and coverage, SEA employs hierarchical retrieval across document and paragraph levels, and constructs a relation directed acyclic graph to model error propagation and identify systematic failure modes. Empirically, SEA uncovers 40.7x more knowledge errors than Automated Capability Discovery and 26.7% more than AutoBencher, while reducing the cost-per-error by 599x and 9x, respectively. Human evaluation confirms the high quality of generated questions, while ablation and convergence analyses validate the contribution of each component in SEA. Further analysis on the discovered errors reveals correlated failure patterns across LLM families and recurring deficits, highlighting the need for better data coverage and targeted fine-tuning in future LLM development.

When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus on measuring their reliability. To understand the potential ramifications of this gap, we investigate how well current benchmarks quantify model reliability. We find that pervasive label errors can compromise these evaluations, obscuring lingering model failures and hiding unreliable behavior. Motivated by this gap in the evaluation of reliability, we then propose the concept of so-called platinum benchmarks, i.e., benchmarks carefully curated to minimize label errors and ambiguity. As a first attempt at constructing such benchmarks, we revise examples from fifteen existing popular benchmarks. We evaluate a wide range of models on these platinum benchmarks and find that, indeed, frontier LLMs still exhibit failures on simple tasks such as elementary-level math word problems. Analyzing these failures further reveals previously unidentified patterns of problems on which frontier models consistently struggle. We provide code at https://github.com/MadryLab/platinum-benchmarks

Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reasoning failures persist, occurring even in seemingly simple scenarios. To systematically understand and address these shortcomings, we present the first comprehensive survey dedicated to reasoning failures in LLMs. We introduce a novel categorization framework that distinguishes reasoning into embodied and non-embodied types, with the latter further subdivided into informal (intuitive) and formal (logical) reasoning. In parallel, we classify reasoning failures along a complementary axis into three types: fundamental failures intrinsic to LLM architectures that broadly affect downstream tasks; application-specific limitations that manifest in particular domains; and robustness issues characterized by inconsistent performance across minor variations. For each reasoning failure, we provide a clear definition, analyze existing studies, explore root causes, and present mitigation strategies. By unifying fragmented research efforts, our survey provides a structured perspective on systemic weaknesses in LLM reasoning, offering valuable insights and guiding future research towards building stronger, more reliable, and robust reasoning capabilities. We additionally release a comprehensive collection of research works on LLM reasoning failures, as a GitHub repository at https://github.com/Peiyang-Song/Awesome-LLM-Reasoning-Failures, to provide an easy entry point to this area.

Large language models (LLMs) show promise in medical diagnosis, but real-world deployment remains challenging due to high-stakes clinical decisions and imperfect reasoning reliability. As a result, careful inspection of model behavior is essential for assessing whether diagnostic reasoning is reliable and clinically grounded. However, debugging medical LLMs remains difficult. First, developers often lack sufficient medical domain expertise to interpret model errors in clinically meaningful terms. Second, models can fail across a large and diverse set of instances involving different input types, tasks, and reasoning steps, making it challenging for developers to prioritize which errors deserve focused inspection. Third, developers struggle to identify recurring error patterns across cases, as existing debugging practices are largely instance-centric and rely on manual inspection of isolated failures. To address these challenges, we present VeriLLMed, a visual analytics system that integrates external biomedical knowledge to audit and debug medical LLM diagnostic reasoning. VeriLLMed transforms model outputs into comparable reasoning paths, constructs knowledge graph-grounded reference paths, and identifies three recurring classes of diagnosis errors: relation errors, branch errors, and missing errors. Case studies and expert evaluation demonstrate that VeriLLMed helps developers identify clinically implausible reasoning and generate actionable insights that can inform the improvement of medical LLMs.

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a novel benchmark of 115 failed trajectories spanning structured API workflows, incident management, and open-ended web/file tasks. Each trajectory is annotated with a critical failure step and a category from a grounded-theory derived, cross-domain failure taxonomy. To mitigate the human cost of failure attribution, we present AGENTRX, an automated domain-agnostic diagnostic framework that pinpoints the critical failure step in a failed agent trajectory. It synthesizes constraints, evaluates them step-by-step, and produces an auditable validation log of constraint violations with associated evidence; an LLM-based judge uses this log to localize the critical step and category. Our framework improves step localization and failure attribution over existing baselines across three domains.

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in LLMs' internal representations, and researchers have proposed using such probing methods for safety detection. We systematically re-examine this paradigm. Motivated by poor out-of-distribution performance, we hypothesize that probes learn superficial patterns rather than semantic harmfulness. Through controlled experiments, we confirm this hypothesis and identify the specific patterns learned: instructional patterns and trigger words. Our investigation follows a systematic approach, progressing from demonstrating comparable performance of simple n-gram methods, to controlled experiments with semantically cleaned datasets, to detailed analysis of pattern dependencies. These results reveal a false sense of security around current probing-based approaches and highlight the need to redesign both models and evaluation protocols, for which we provide further discussions in the hope of suggesting responsible further research in this direction. We have open-sourced the project at https://github.com/WangCheng0116/Why-Probe-Fails.

We study inference-time pattern-memory gating in a production-scale clinical natural language processing (NLP) pipeline. The pipeline pairs a generator (Llama-3.3 70B) proposing extractions with a verifier (MMed-Llama-3.1 70B) accepting or rejecting them, over 167,034 PMC-Patients narratives, and adds a lightweight memory that learns at deployment which extractions to filter, so the verifier need not re-examine candidates already seen to fail. We report four findings. First, learning filtering rules directly from the verifier's rejections failed at full scale: the relation-extraction filter stayed empty despite 785,797 logged rejections, because they were spread too thinly across too many distinct forms to accumulate. Second, a simpler rule using a fixed clinical ontology produced the same filtering without the verifier, capturing 49,734 ontology-violating relations on a held-out 5,000-patient set. Third, of five versions of the question-answering filter, four failed for distinct, instructive reasons; the fifth succeeded by checking whether a patient's extracted entities support the question asked, and where it applies was 1.84 times likelier to flag an answer the verifier would reject than one it would accept. Fourth, one pattern held across all five: a filter is selective only when it tests the same evidence the verifier weighs, not when it imitates the verifier's output. Together these give a transferable result for any generator-verifier pipeline: the most natural memory design can fail silently at scale, and whether a pre-generation gate is selective is decided before any engineering effort, by whether its signal probes the question the verifier itself answers. Throughout, the system flags suspect extractions rather than deleting them, so every decision stays visible for clinical review. All code and test artefacts are released openly.

Machine learning models can make critical errors that are easily hidden within vast amounts of data. Such errors often run counter to rules based on human intuition. However, rules based on human knowledge are challenging to scale or to even formalize. We thereby seek to infer statistical rules from the data and quantify the extent to which a model has learned them. We propose a framework SQRL that integrates logic-based methods with statistical inference to derive these rules from a model's training data without supervision. We further show how to adapt models at test time to reduce rule violations and produce more coherent predictions. SQRL generates up to 300K rules over datasets from vision, tabular, and language settings. We uncover up to 158K violations of those rules by state-of-the-art models for classification, object detection, and data imputation. Test-time adaptation reduces these violations by up to 68.7% with relative performance improvement up to 32%. SQRL is available at https://github.com/DebugML/sqrl.

Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscures true learning dynamics. In this work, we systematically diagnose this instability, attributing it to two distinct sources: Parameter Instability from training stochasticity and Evaluation Instability from noisy measurement protocols. To counteract both sources of noise, we introduce MaP, a dual-pronged framework that synergistically integrates checkpoint Merging and the Pass@k metric. Checkpoint merging smooths the parameter space by averaging recent model weights, while Pass@k provides a robust, low-variance statistical estimate of model capability. Extensive experiments show that MaP yields significantly smoother performance curves, reduces inter-run variance, and ensures more consistent model rankings. Ultimately, MaP provides a more reliable and faithful lens for observing LLM training dynamics, laying a crucial empirical foundation for LLM research.

Tool-using automation systems, from scripts and CI bots to agentic assistants, fail in recurring patterns. Common failures include unsafe side effects, invalid arguments, uncontrolled retries, and leakage of sensitive outputs. Many mitigations are model-centric and prompt-dependent, so they are brittle and do not generalize to non-LLM callers. We present Policy-First Tooling, a model-agnostic permission layer that mediates tool invocation through explicit constraints, risk-aware gating, recovery controls, and auditable explanations. The paper contributes a compact policy DSL, a runtime enforcement architecture with actionable rationale and fix hints, and a reproducible benchmark based on trace replay with controlled fault and misuse injection. In 225 controlled runs across five policy packs and three fault profiles, stricter packs improve violation prevention from 0.000 in P0 to 0.681 in P4, while task success drops from 0.356 to 0.067. Retry amplification decreases from 3.774 in P0 to 1.378 in P4, and leakage recall reaches 0.875 under injected secret outputs. These results make safety to utility trade-offs explicit and measurable.

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant feature-via prompt-based jailbreaks-can cause alignment to collapse, leading to unsafe generation. Motivated by this, we propose fail-closed alignment as a design principle for robust LLM safety: refusal mechanisms should remain effective even under partial failures via redundant, independent causal pathways. We present a concrete instantiation of this principle: a progressive alignment framework that iteratively identifies and ablates previously learned refusal directions, forcing the model to reconstruct safety along new, independent subspaces. Across four jailbreak attacks, we achieve the strongest overall robustness while mitigating over-refusal and preserving generation quality, with small computational overhead. Our mechanistic analyses confirm that models trained with our method encode multiple, causally independent refusal directions that prompt-based jailbreaks cannot suppress simultaneously, providing empirical support for fail-closed alignment as a principled foundation for robust LLM safety.

We propose a new long-context financial benchmark, FailSafeQA, designed to test the robustness and context-awareness of LLMs against six variations in human-interface interactions in LLM-based query-answer systems within finance. We concentrate on two case studies: Query Failure and Context Failure. In the Query Failure scenario, we perturb the original query to vary in domain expertise, completeness, and linguistic accuracy. In the Context Failure case, we simulate the uploads of degraded, irrelevant, and empty documents. We employ the LLM-as-a-Judge methodology with Qwen2.5-72B-Instruct and use fine-grained rating criteria to define and calculate Robustness, Context Grounding, and Compliance scores for 24 off-the-shelf models. The results suggest that although some models excel at mitigating input perturbations, they must balance robust answering with the ability to refrain from hallucinating. Notably, Palmyra-Fin-128k-Instruct, recognized as the most compliant model, maintained strong baseline performance but encountered challenges in sustaining robust predictions in 17% of test cases. On the other hand, the most robust model, OpenAI o3-mini, fabricated information in 41% of tested cases. The results demonstrate that even high-performing models have significant room for improvement and highlight the role of FailSafeQA as a tool for developing LLMs optimized for dependability in financial applications. The dataset is available at: https://huggingface.co/datasets/Writer/FailSafeQA

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. This paper explores the problem of building ML systems that fail loudly, investigating methods for detecting dataset shift, identifying exemplars that most typify the shift, and quantifying shift malignancy. We focus on several datasets and various perturbations to both covariates and label distributions with varying magnitudes and fractions of data affected. Interestingly, we show that across the dataset shifts that we explore, a two-sample-testing-based approach, using pre-trained classifiers for dimensionality reduction, performs best. Moreover, we demonstrate that domain-discriminating approaches tend to be helpful for characterizing shifts qualitatively and determining if they are harmful.

We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks. Existing evaluations conflate representation quality with model capacity. Therefore, failures cannot be attributed to the representation rather than to the model that processes it. We formalize four functional axioms (Causality, Minimality, Separability, and Stability) and define a quantitative measure for each, computed directly on the representation independently of downstream accuracy. We audit open-weight LLMs across 23 reasoning tasks (e.g., Spatial Reasoning, Factual QA). We find that no candidate satisfies all four axioms simultaneously, that the representations distinguish task type reliably but cannot distinguish between two questions within the same task, and that the representations encode little information beyond what is already present in the input embedding. The failure is consistent across dense, reasoning-distilled, and RL-trained model families, indicating that the gap is structural rather than a property of model size or training procedure.

Shojaee et al. (2025) report that Large Reasoning Models (LRMs) exhibit "accuracy collapse" on planning puzzles beyond certain complexity thresholds. We demonstrate that their findings primarily reflect experimental design limitations rather than fundamental reasoning failures. Our analysis reveals three critical issues: (1) Tower of Hanoi experiments systematically exceed model output token limits at reported failure points, with models explicitly acknowledging these constraints in their outputs; (2) The authors' automated evaluation framework fails to distinguish between reasoning failures and practical constraints, leading to misclassification of model capabilities; (3) Most concerningly, their River Crossing benchmarks include mathematically impossible instances for N > 5 due to insufficient boat capacity, yet models are scored as failures for not solving these unsolvable problems. When we control for these experimental artifacts, by requesting generating functions instead of exhaustive move lists, preliminary experiments across multiple models indicate high accuracy on Tower of Hanoi instances previously reported as complete failures. These findings highlight the importance of careful experimental design when evaluating AI reasoning capabilities.

We report a case study of four end-to-end attempts to autonomously generate ML research papers using a pipeline of six LLM agents mapped to stages of the scientific workflow. Of these four, three attempts failed during implementation or evaluation. One completed the pipeline and was accepted to Agents4Science 2025, an experimental inaugural venue that required AI systems as first authors, passing both human and multi-AI review. From these attempts, we document six recurring failure modes: bias toward training data defaults, implementation drift under execution pressure, memory and context degradation across long-horizon tasks, overexcitement that declares success despite obvious failures, insufficient domain intelligence, and weak scientific taste in experimental design. We conclude by discussing four design principles for more robust AI-scientist systems, implications for autonomous scientific discovery, and we release all prompts, artifacts, and outputs at https://github.com/Lossfunk/ai-scientist-artefacts-v1

Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after convergence, models often fail to correctly reproduce a subset of their own supervised training data. We refer to this behavior as the Incomplete Learning Phenomenon(ILP). This paper presents the first systematic study of ILP in LLM fine-tuning. We formalize ILP as post-training failure to internalize supervised instances and demonstrate its prevalence across multiple model families, domains, and datasets. Through controlled analyses, we identify five recurrent sources of incomplete learning: (1) missing prerequisite knowledge in the pre-trained model, (2) conflicts between SFT supervision and pre-training knowledge, (3) internal inconsistencies within SFT data, (4) left-side forgetting during sequential fine-tuning, and (5) insufficient optimization for rare or complex patterns. We introduce a diagnostic-first framework that maps unlearned samples to these causes using observable training and inference signals, and study several targeted mitigation strategies as causal interventions. Experiments on Qwen, LLaMA, and OLMo2 show that incomplete learning is widespread and heterogeneous, and that improvements in aggregate metrics can mask persistent unlearned subsets. The findings highlight the need for fine-grained diagnosis of what supervised fine-tuning fails to learn, and why.

LLM failures in causal reasoning, including sycophancy, rung collapse, and miscalibrated refusal, are well-documented, yet progress on remediation is slow because no benchmark enables systematic diagnosis. We introduce CausalT5K, a diagnostic benchmark of over 5,000 cases across 10 domains that tests three critical capabilities: (1) detecting rung collapse, where models answer interventional queries with associational evidence; (2) resisting sycophantic drift under adversarial pressure; and (3) generating Wise Refusals that specify missing information when evidence is underdetermined. Unlike synthetic benchmarks, CausalT5K embeds causal traps in realistic narratives and decomposes performance into Utility (sensitivity) and Safety (specificity), revealing failure modes invisible to aggregate accuracy. Developed through a rigorous human-machine collaborative pipeline involving 40 domain experts, iterative cross-validation cycles, and composite verification via rule-based, LLM, and human scoring, CausalT5K implements Pearl's Ladder of Causation as research infrastructure. Preliminary experiments reveal a Four-Quadrant Control Landscape where static audit policies universally fail, a finding that demonstrates CausalT5K's value for advancing trustworthy reasoning systems. Repository: https://github.com/genglongling/CausalT5kBench

We introduce FailureSensorIQ, a novel Multi-Choice Question-Answering (MCQA) benchmarking system designed to assess the ability of Large Language Models (LLMs) to reason and understand complex, domain-specific scenarios in Industry 4.0. Unlike traditional QA benchmarks, our system focuses on multiple aspects of reasoning through failure modes, sensor data, and the relationships between them across various industrial assets. Through this work, we envision a paradigm shift where modeling decisions are not only data-driven using statistical tools like correlation analysis and significance tests, but also domain-driven by specialized LLMs which can reason about the key contributors and useful patterns that can be captured with feature engineering. We evaluate the Industrial knowledge of over a dozen LLMs-including GPT-4, Llama, and Mistral-on FailureSensorIQ from different lens using Perturbation-Uncertainty-Complexity analysis, Expert Evaluation study, Asset-Specific Knowledge Gap analysis, ReAct agent using external knowledge-bases. Even though closed-source models with strong reasoning capabilities approach expert-level performance, the comprehensive benchmark reveals a significant drop in performance that is fragile to perturbations, distractions, and inherent knowledge gaps in the models. We also provide a real-world case study of how LLMs can drive the modeling decisions on 3 different failure prediction datasets related to various assets. We release: (a) expert-curated MCQA for various industrial assets, (b) FailureSensorIQ benchmark and Hugging Face leaderboard based on MCQA built from non-textual data found in ISO documents, and (c) LLMFeatureSelector, an LLM-based feature selection scikit-learn pipeline. The software is available at https://github.com/IBM/FailureSensorIQ.

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial" study of LLMs to benchmark their capability in generating causal arguments. Across a wide range of tasks, we find that LLMs can generate text corresponding to correct causal arguments with high probability, surpassing the best-performing existing methods. Algorithms based on GPT-3.5 and 4 outperform existing algorithms on a pairwise causal discovery task (97%, 13 points gain), counterfactual reasoning task (92%, 20 points gain) and event causality (86% accuracy in determining necessary and sufficient causes in vignettes). We perform robustness checks across tasks and show that the capabilities cannot be explained by dataset memorization alone, especially since LLMs generalize to novel datasets that were created after the training cutoff date. That said, LLMs exhibit unpredictable failure modes, and we discuss the kinds of errors that may be improved and what are the fundamental limits of LLM-based answers. Overall, by operating on the text metadata, LLMs bring capabilities so far understood to be restricted to humans, such as using collected knowledge to generate causal graphs or identifying background causal context from natural language. As a result, LLMs may be used by human domain experts to save effort in setting up a causal analysis, one of the biggest impediments to the widespread adoption of causal methods. Given that LLMs ignore the actual data, our results also point to a fruitful research direction of developing algorithms that combine LLMs with existing causal techniques. Code and datasets are available at https://github.com/py-why/pywhy-llm.

Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most powerful large language models (LLMs). To study these abilities under controlled settings, we introduce TopoBench, a benchmark of six puzzle families across three difficulty levels. We evaluate strong reasoning LLMs on TopoBench and find that even frontier models solve fewer than one quarter of hard instances, with two families nearly unsolved. To investigate whether these failures stem from reasoning limitations or from difficulty extracting and maintaining spatial constraints, we annotate 750 chain of thought traces with an error taxonomy that surfaces four candidate causal failure modes, then test them with targeted interventions simulating each error type. These interventions show that certain error patterns like premature commitment and constraint forgetting have a direct impact on the ability to solve the puzzle, while repeated reasoning is a benign effect of search. Finally we study mitigation strategies including prompt guidance, cell-aligned grid representations and tool-based constraint checking, finding that the bottleneck lies in extracting constraints from spatial representations and not in reasoning over them. Code and data are available at github.com/mayug/topobench-benchmark.

Large language models (LLMs) are being rapidly integrated into decision-support tools, automation workflows, and AI-enabled software systems. However, their behavior in production environments remains poorly understood, and their failure patterns differ fundamentally from those of traditional machine learning models. This paper presents a system-level taxonomy of fifteen hidden failure modes that arise in real-world LLM applications, including multi-step reasoning drift, latent inconsistency, context-boundary degradation, incorrect tool invocation, version drift, and cost-driven performance collapse. Using this taxonomy, we analyze the growing gap in evaluation and monitoring practices: existing benchmarks measure knowledge or reasoning but provide little insight into stability, reproducibility, drift, or workflow integration. We further examine the production challenges associated with deploying LLMs - including observability limitations, cost constraints, and update-induced regressions - and outline high-level design principles for building reliable, maintainable, and cost-aware LLM systems. Finally, we outline high-level design principles for building reliable, maintainable, and cost-aware LLM-based systems. By framing LLM reliability as a system-engineering problem rather than a purely model-centric one, this work provides an analytical foundation for future research on evaluation methodology, AI system robustness, and dependable LLM deployment.

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora. Logics-STEM targets reasoning tasks in the domains of Science, Technology, Engineering, and Mathematics (STEM), and exhibits exceptional performance on STEM-related benchmarks with an average improvement of 4.68% over the next-best model at 8B scale. We attribute the gains to our data-algorithm co-design engine, where they are jointly optimized to fit a gold-standard distribution behind reasoning. Data-wise, the Logics-STEM-SFT-Dataset is constructed from a meticulously designed data curation engine with 5 stages to ensure the quality, diversity, and scalability, including annotation, deduplication, decontamination, distillation, and stratified sampling. Algorithm-wise, our failure-driven post-training framework leverages targeted knowledge retrieval and data synthesis around model failure regions in the Supervised Fine-tuning (SFT) stage to effectively guide the second-stage SFT or the reinforcement learning (RL) for better fitting the target distribution. The superior empirical performance of Logics-STEM reveals the vast potential of combining large-scale open-source data with carefully designed synthetic data, underscoring the critical role of data-algorithm co-design in enhancing reasoning capabilities through post-training. We make both the Logics-STEM models (8B and 32B) and the Logics-STEM-SFT-Dataset (10M and downsampled 2.2M versions) publicly available to support future research in the open-source community.

Machine learning models always make a prediction, even when it is likely to be inaccurate. This behavior should be avoided in many decision support applications, where mistakes can have severe consequences. Albeit already studied in 1970, machine learning with rejection recently gained interest. This machine learning subfield enables machine learning models to abstain from making a prediction when likely to make a mistake. This survey aims to provide an overview on machine learning with rejection. We introduce the conditions leading to two types of rejection, ambiguity and novelty rejection, which we carefully formalize. Moreover, we review and categorize strategies to evaluate a model's predictive and rejective quality. Additionally, we define the existing architectures for models with rejection and describe the standard techniques for learning such models. Finally, we provide examples of relevant application domains and show how machine learning with rejection relates to other machine learning research areas.

Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on conflicts: when the document contradicts pretraining knowledge, accuracy collapses to 46.4% on the deepest facts. We show the failure is a magnitude problem rather than a representational one. The hypernetwork already targets the right layers, but its adapter margin is approximately constant across documents while the pretrained margin grows with training frequency, so deep conflicts lose by construction. The account predicts that failure should track prior strength: sorting 194 conflicts by the base model's log-probability on the contradicted fact, baseline accuracy falls from 68% on weak-prior questions to 16% on strong-prior ones, a 52 percentage-point gap. The cure is amplitude. Selective Layer Boosting scales the adapter at its top-norm layers, and Conflict-Aware Internalization triggers boosting only when the base model is confident. Both are training-free; together they raise deep-conflict accuracy from 46.4% to 71.0% on Gemma-2B and from 53.6% to 72.5% on Mistral-7B while preserving novel-knowledge recall, and beat vanilla retrieval-augmented generation on medium conflicts by 18 percentage points despite operating entirely in parameter space. We release KID-Bench, a 489-question benchmark that separates novel recall, cross-knowledge combination, and prior-graded conflicts.

Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents. Yet MCP-style tool use requires more than isolated function calling: an agent must discover tools from live catalogs, satisfy schemas, preserve dependencies across intermediate outputs, and ground final responses in executed evidence. Small planners often generate plausible workflow graphs that fail under tool resolution, parameter validation, dependency tracking, or execution. We argue that this failure mode is poorly handled by small-corpus distillation. A few hundred teacher traces can teach workflow format, but rarely cover the recovery behavior needed to repair failed plans over changing tool catalogs. We introduce Evoflux, an inference-time evolutionary search method that treats compact tool use as the repair of executable tool workflows. It evolves typed workflow graphs through structured edits, execution feedback, adaptive intensity, meta-guided redesign, and diversity pruning. On held-out MCP-Bench tasks spanning live MCP servers and 250 tools, Evoflux raises execution feasibility from roughly 3% to 17-24% across small planners. In contrast, SFT and SFT+DPO on the same search-mined data match, underperform, or collapse below zero-shot performance; ReAct reaches higher peaks, but with higher variance and token cost. These results show that execution-grounded search is more reliable under scarce teacher-trace budgets.

Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully. In policy-permissive environments, a tool may execute any well-formed call even when the corresponding state transition is forbidden by domain policy. The result is a silent wrong state (a booking cancelled, a passenger count changed, a claim acted on without verification) that neither the tool nor the agent's self-report exposes. We study this failure mode in the τ^2-bench airline domain. On a budget agent, 78% of observed failures are silent wrong-state failures with no tool error, and the aggregate failure rate is reproducible across disjoint seeds, not sampling noise. We then evaluate a lightweight intervention: deterministic, read-only pre-execution gates that inspect the proposed call and current state before allowing a write. A four-gate suite raises full-benchmark success from 29.6% to 42.0% on gpt-4o-mini (+12.4pp; paired task-level bootstrap P=0.0012), and the lift reproduces on a disjoint 15-seed set (+12.3pp; P=0.0008). The effect is concentrated where the gates fire: on the 26/50 firing tasks, success rises by +19.2pp, while movement on the 24 non-firing tasks does not exclude zero. Two negative controls (a self-enforcing retail domain and BFCL) bound the mechanism: gates help when tools are policy-permissive and add little where tools already self-enforce. As suggestive evidence, not a central claim, the same failure mode persists at the frontier: gpt-5.2 at default reasoning still attempts policy-violating writes, and the same suite improves success from 61.2% to 71.6% (+10.4pp; P=0.020; n=5, no replication). The contribution is a bounded evaluation and reliability result: deterministic gates do not guarantee task success, but they can deterministically prevent a known class of silent policy-violating writes at the action boundary.

Despite their recent successes, Transformer-based large language models show surprising failure modes. A well-known example of such failure modes is their inability to length-generalize: solving problem instances at inference time that are longer than those seen during training. In this work, we further explore the root cause of this failure by performing a detailed analysis of model behaviors on the simple parity task. Our analysis suggests that length generalization failures are intricately related to a model's inability to perform random memory accesses within its context window. We present supporting evidence for this hypothesis by demonstrating the effectiveness of methodologies that circumvent the need for indexing or that enable random token access indirectly, through content-based addressing. We further show where and how the failure to perform random memory access manifests through attention map visualizations.

As modern microservice systems grow increasingly popular and complex-often consisting of hundreds or even thousands of fine-grained, interdependent components-they are becoming more susceptible to frequent and subtle failures. Ensuring system reliability therefore hinges on accurate and efficient failure localization. Traditional failure localization approaches based on small models lack the flexibility to adapt to diverse failure scenarios, while recent LLM-based methods suffer from two major limitations: they often rely on rigid invocation workflows that constrain the model's ability to dynamically explore optimal localization paths, and they require resource-intensive inference, making them cost-prohibitive for real-world deployment. To address these challenges, we explore the use of reinforcement fine-tuning to equip lightweight LLMs with reasoning and self-refinement capabilities, significantly improving the cost-effectiveness and adaptability of LLM-based failure localization. We begin with an empirical study to identify three key capabilities essential for accurate localization. Building on these insights, we propose a progressive multi-stage GRPO fine-tuning framework, which integrates a multi-factor failure localization grader and a recursion-of-thought actor module. The resulting model, ThinkFL, not only outperforms existing state-of-the-art LLMs and baseline methods in localization accuracy but also reduces end-to-end localization latency from minutes to seconds, demonstrating strong potential for real-world applications.

Text-guided diffusion models (TDMs) are widely applied but can fail unexpectedly. Common failures include: (i) natural-looking text prompts generating images with the wrong content, or (ii) different random samples of the latent variables that generate vastly different, and even unrelated, outputs despite being conditioned on the same text prompt. In this work, we aim to study and understand the failure modes of TDMs in more detail. To achieve this, we propose SAGE, the first adversarial search method on TDMs that systematically explores the discrete prompt space and the high-dimensional latent space, to automatically discover undesirable behaviors and failure cases in image generation. We use image classifiers as surrogate loss functions during searching, and employ human inspections to validate the identified failures. For the first time, our method enables efficient exploration of both the discrete and intricate human language space and the challenging latent space, overcoming the gradient vanishing problem. Then, we demonstrate the effectiveness of SAGE on five widely used generative models and reveal four typical failure modes: (1) We find a variety of natural text prompts that generate images failing to capture the semantics of input texts. We further discuss the underlying causes and potential solutions based on the results. (2) We find regions in the latent space that lead to distorted images independent of the text prompt, suggesting that parts of the latent space are not well-structured. (3) We also find latent samples that result in natural-looking images unrelated to the text prompt, implying a possible misalignment between the latent and prompt spaces. (4) By appending a single adversarial token embedding to any input prompts, we can generate a variety of specified target objects. Project page: https://sage-diffusion.github.io/

Modern analyst agents must reason over complex, high token inputs, including dozens of retrieved documents, tool outputs, and time sensitive data. While prior work has produced tool calling benchmarks and examined factuality in knowledge augmented systems, relatively little work studies their intersection: settings where LLMs must integrate large volumes of dynamic, structured and unstructured multi tool outputs. We investigate LLM failure modes in this regime using crypto as a representative high data density domain. We introduce (1) CryptoAnalystBench, an analyst aligned benchmark of 198 production crypto and DeFi queries spanning 11 categories; (2) an agentic harness equipped with relevant crypto and DeFi tools to generate responses across multiple frontier LLMs; and (3) an evaluation pipeline with citation verification and an LLM as a judge rubric spanning four user defined success dimensions: relevance, temporal relevance, depth, and data consistency. Using human annotation, we develop a taxonomy of seven higher order error types that are not reliably captured by factuality checks or LLM based quality scoring. We find that these failures persist even in state of the art systems and can compromise high stakes decisions. Based on this taxonomy, we refine the judge rubric to better capture these errors. While the judge does not align with human annotators on precise scoring across rubric iterations, it reliably identifies critical failure modes, enabling scalable feedback for developers and researchers studying analyst style agents. We release CryptoAnalystBench with annotated queries, the evaluation pipeline, judge rubrics, and the error taxonomy, and outline mitigation strategies and open challenges in evaluating long form, multi tool augmented systems.

Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown: the model "loses the thread" mid-reasoning. We study whether such breakdowns are detectable from inference-time observables available in standard APIs (token log probabilities), without any training or fine-tuning. We define a simple instability signal that combines consecutive-step distributional shift (JSD) and uncertainty (entropy), summarize each trace by its peak instability strength, and show that this signal reliably predicts failure. Across GSM8K and HotpotQA, instability strength predicts wrong answers with above-chance AUC and yields monotonic bucket-level accuracy decline at scale across model sizes. Crucially, we show that instability is not uniformly harmful: early instability can reflect subsequent stabilization and a correct final answer (corrective instability), whereas late instability is more often followed by failure (destructive instability), even at comparable peak magnitudes, indicating that recoverability depends not only on how strongly the distribution changes but also on when such changes occur relative to the remaining decoding horizon. The method is model-agnostic, training-free, and reproducible, and is presented as a diagnostic lens rather than a corrective or control mechanism.

This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning. Covering three practical domains -- airline baggage fees, NBA transactions, and tax regulations -- RuleArena assesses LLMs' proficiency in handling intricate natural language instructions that demand long-context understanding, logical reasoning, and accurate mathematical computation. Two key attributes distinguish RuleArena from traditional rule-based reasoning benchmarks: (1) it extends beyond standard first-order logic representations, and (2) it is grounded in authentic, practical scenarios, providing insights into the suitability and reliability of LLMs for real-world applications. Our findings reveal several notable limitations in LLMs: (1) they struggle to identify and apply the appropriate rules, frequently becoming confused by similar but distinct regulations, (2) they cannot consistently perform accurate mathematical computations, even when they correctly identify the relevant rules, and (3) in general, they perform poorly in the benchmark. These results highlight significant challenges in advancing LLMs' rule-guided reasoning capabilities in real-life applications.

Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs). However, standard RL assigns credit only at the level of the final answer, penalizing entire reasoning traces when the outcome is incorrect and uniformly reinforcing all steps when it is correct. As a result, correct intermediate steps may be discouraged in failed traces, while spurious steps may be reinforced in successful ones. We refer to this failure mode as the problem of credit assignment. While a natural remedy is to train a process reward model, accurately optimizing such models to identify corrective reasoning steps remains challenging. We introduce Intervention Training (InT), a training paradigm in which the model performs fine-grained credit assignment on its own reasoning traces by proposing short, targeted corrections that steer trajectories toward higher reward. Using reference solutions commonly available in mathematical reasoning datasets and exploiting the fact that verifying a model-generated solution is easier than generating a correct one from scratch, the model identifies the first error in its reasoning and proposes a single-step intervention to redirect the trajectory toward the correct solution. We then apply supervised fine-tuning (SFT) to the on-policy rollout up to the point of error concatenated with the intervention, localizing error to the specific step that caused failure. We show that the resulting model serves as a far better initialization for RL training. After running InT and subsequent fine-tuning with RL, we improve accuracy by nearly 14% over a 4B-parameter base model on IMO-AnswerBench, outperforming larger open-source models such as gpt-oss-20b.

We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward discovery on real scientific problems. NatureBench is built on NatureGym, an automated pipeline that constructs a standardized, per-task containerized environment from a source paper, addressing the environment-fragmentation problem that has limited the credibility of prior agent-on-research benchmarks. Evaluating ten frontier agent configurations under a strict web-search-disabled protocol, we find that the strongest model surpasses SOTA on only 17.8% of tasks under the g>0.1 criterion. Analysis of method pathways reveals that agents succeed primarily through methodological translation, converting scientific tasks into familiar supervised prediction problems, rather than through genuine scientific invention. Failures are dominated by wrong method choice and insufficient compute budget, not by task misunderstanding. We release the benchmark, the NatureGym pipeline, and a public leaderboard with maintainer-side reproduction. Code: https://github.com/FrontisAI/NatureBench

Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records of hazard, exposure, vulnerability, and lifeline infrastructure that underpin disaster management. Current text-to-SQL methods enable natural-language access to such tables but transfer poorly to the disaster domain, where queries span heterogeneous geospatial schemas and require reasoning over causal relations. We introduce DisasterLex, a knowledge-graph-mediated framework that inserts an Expert Knowledge Graph (EKG) of curated concepts and typed causal edges between the user query and the database, bridged to schema by concept-to-table links. The orchestration runs four stages (identifying query entities, routing to the operational domain, planning over causal edges, and grounding the SQL), restricting the schema passed to the model at each step. We instantiate it on a disaster-analytics database (36 geospatial tables, 150 columns) with an EKG of 107 concepts, 117 causal edges, and 52 concept-to-schema links, evaluated on a 75-query test set. On all seven base models spanning proprietary and open-weight families, DisasterLex beats four state-of-the-art baselines (LightRAG, HippoRAG 2, ReFoRCE, CHESS) by 1.4x to 2.75x, with absolute scores of 1.65 to 3.56 (of 5.0). Error analysis shows baseline failures cluster in routing and multi-table SQL composition, the operations our orchestration explicitly addresses. Code, data, and the EKG artifact are available at https://github.com/YimingXiao98/DisasterLex and on Zenodo at https://doi.org/10.5281/zenodo.20388029.

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes (I'm sorry). We demonstrate that this rigid refusal pattern is a vulnerability and introduce a novel refusal unlearning technique that exploits it. Specifically, we fine-tune LLMs using merely 1,000 benign samples, where each response is prepended with a refusal prefix. The underlying intuition is to disrupt the refusal completion pathway, thereby driving the model to forget how to refuse while following harmful instructions. This intuition is further supported by theoretical proofs. We apply this approach to a total of 16 LLMs, including various open-source models from Llama, Qwen, and Gemma families, as well as closed-source models such as Gemini and GPT. Experimental results show that the safety scores of previously aligned LLMs degrade both consistently and substantially. Importantly, we verify that the observed gain cannot be attributed to plain fine-tuning or random prefix effects. Our findings suggest that current safety alignment may rely heavily on token sequence memorization rather than reasoning, motivating future work beyond simple refusal mechanisms. Code has been released: https://github.com/guoyang9/refusal-unlearning.

Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three surprising facts: (a) Failure of extremely simple puzzles, e.g., HRM can fail on a puzzle with only one unknown cell. We attribute this failure to the violation of the fixed point property, a fundamental assumption of HRM. (b) "Grokking" dynamics in reasoning steps, i.e., the answer is not improved uniformly, but instead there is a critical reasoning step that suddenly makes the answer correct; (c) Existence of multiple fixed points. HRM "guesses" the first fixed point, which could be incorrect, and gets trapped there for a while or forever. All facts imply that HRM appears to be "guessing" instead of "reasoning". Leveraging this "guessing" picture, we propose three strategies to scale HRM's guesses: data augmentation (scaling the quality of guesses), input perturbation (scaling the number of guesses by leveraging inference randomness), and model bootstrapping (scaling the number of guesses by leveraging training randomness). On the practical side, by combining all methods, we develop Augmented HRM, boosting accuracy on Sudoku-Extreme from 54.5% to 96.9%. On the scientific side, our analysis provides new insights into how reasoning models "reason".

Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do not by themselves produce research judgment. We analyze where current systems lose trial experience: weak evidence becomes prose, pilot signals become broad claims, memory remains textual, and recurring process failures do not change later behavior. We introduce Sibyl-AutoResearch, a self-evolving AutoResearch framework built around Scientific Trial-and-Error Harnesses. A harness lets agents run bounded trials, preserve positive and negative outcomes, and route lessons into later planning, validation, claim scope, scheduling, critique, writing, and harness repair. We formalize this through two auditable conversion units: trial-to-behavior conversion, which links trial signals to later research actions, and trial-to-harness-behavior conversion, which links recurring process failures to system updates. We implement the framework in SIBYL, a file-backed autonomous research system that exposes the state, roles, memory, gates, and artifact traces needed to inspect these conversion paths. A retrospective audit identifies eight high-confidence conversion events, with a median latency of one iteration and a maximum latency of three iterations. A recovered-failure registry further shows how five naturally occurring failure classes, including duplicate results, stale numbers, and unsupported statistics, were blocked, downgraded, or routed into later repair. These traces do not establish a comparative performance claim; they show that the proposed conversion units are recoverable from realistic autonomous-research workspaces. The SIBYL framework and system are available at https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem.

In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not limited to incorrect final outputs. They also arise from long-horizon interaction, stochastic decisions, and external side effects (such as API calls, database writes, and message sends). Common failures include non-termination, role drift, propagation of unsupported claims, and attacks via untrusted context or external channels. This paper presents an assurance framework for such Agentic AI systems. Executions are instrumented as Message-Action Traces (MAT) with explicit step and trace contracts. Contracts provide machine-checkable verdicts, localize the first violating step, and support deterministic replay. The framework includes stress testing, formulated as a budgeted counterexample search over bounded perturbations. It also supports structured fault injection at service, retrieval, and memory boundaries to assess containment under realistic operational faults and degraded conditions. Finally, governance is treated as a runtime component, enforcing per-agent capability limits and action mediation (allow, rewrite, block) at the language-to-action boundary. To support comparative evaluations across stochastic seeds, models, and orchestration configurations, the paper defines trace-based metrics for task success, termination reliability, contract compliance, factuality indicators, containment rate, and governance outcome distributions. More broadly, the framework is intended as a common abstraction to support testing and evaluation of multi-agent LLM systems, and to facilitate reproducible comparison across orchestration designs and configurations.

Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover complex task settings, they still largely assume clean, stable, and trustworthy tool environments, leaving tool-environment unreliability insufficiently examined. We introduce ToolBench-X, a benchmark for evaluating agents under recoverable reliability hazards. ToolBench-X contains executable multi-step tasks across diverse domains and sequential, parallel, and mixed workflows, each paired with deterministic tools and a canonical final answer for automatic evaluation. Starting from clean tool environments, ToolBench-X injects five structured hazard types: Specification Drift, Invocation Error, Execution Failure, Output Drift, and Cross-source Conflict. Crucially, each injected instance remains solvable through at least one valid recovery path, such as retrying, fallback, verification, or cross-checking. Experiments reveal a substantial reliability gap: agents that perform well with reliable tools often fail under recoverable hazards. Further analysis shows that failures are driven less by tool-use volume or inference budget than by limited hazard diagnosis and ineffective recovery. Targeted recovery hints recover many failed tasks, while test-time scaling yields more limited gains. These results suggest that tool-use evaluation should move beyond function-call accuracy toward task completion under unreliable tool environments. The code and data is available at https://github.com/Foreverskyou/ToolBench-X.

Recent studies have revealed a number of pathologies of neural machine translation (NMT) systems. Hypotheses explaining these mostly suggest there is something fundamentally wrong with NMT as a model or its training algorithm, maximum likelihood estimation (MLE). Most of this evidence was gathered using maximum a posteriori (MAP) decoding, a decision rule aimed at identifying the highest-scoring translation, i.e. the mode. We argue that the evidence corroborates the inadequacy of MAP decoding more than casts doubt on the model and its training algorithm. In this work, we show that translation distributions do reproduce various statistics of the data well, but that beam search strays from such statistics. We show that some of the known pathologies and biases of NMT are due to MAP decoding and not to NMT's statistical assumptions nor MLE. In particular, we show that the most likely translations under the model accumulate so little probability mass that the mode can be considered essentially arbitrary. We therefore advocate for the use of decision rules that take into account the translation distribution holistically. We show that an approximation to minimum Bayes risk decoding gives competitive results confirming that NMT models do capture important aspects of translation well in expectation.

Deployed multimodal systems can fail in ways that evaluators did not anticipate. In order to find these failures before deployment, we introduce MultiMon, a system that automatically identifies systematic failures -- generalizable, natural-language descriptions of patterns of model failures. To uncover systematic failures, MultiMon scrapes a corpus for examples of erroneous agreement: inputs that produce the same output, but should not. It then prompts a language model (e.g., GPT-4) to find systematic patterns of failure and describe them in natural language. We use MultiMon to find 14 systematic failures (e.g., "ignores quantifiers") of the CLIP text-encoder, each comprising hundreds of distinct inputs (e.g., "a shelf with a few/many books"). Because CLIP is the backbone for most state-of-the-art multimodal systems, these inputs produce failures in Midjourney 5.1, DALL-E, VideoFusion, and others. MultiMon can also steer towards failures relevant to specific use cases, such as self-driving cars. We see MultiMon as a step towards evaluation that autonomously explores the long tail of potential system failures. Code for MULTIMON is available at https://github.com/tsb0601/MultiMon.

Agentic systems consisting of multiple LLM-driven agents coordinating through tools and structured interactions, are increasingly deployed for complex reasoning and problem-solving tasks. At the same time, emerging low-code and template-based agent development platforms (e.g., Dify) enable users to rapidly build and orchestrate agentic systems, which we refer to as platform-orchestrated agentic systems. However, these systems are also fragile and it remains unclear how to systematically identify their potential failure root cause. This paper presents a study of root cause identification of these platform-orchestrated agentic systems. To support this initiative, we construct a dataset AgentFail containing 307 failure logs from ten agentic systems, each with fine-grained annotations linking failures to their root causes. We additionally utilize counterfactual reasoning-based repair strategy to ensure the reliability of the annotation. Building on the dataset, we develop a taxonomy that characterizes failure root causes and analyze their distribution across different platforms and task domains. Furthermore, we introduce a benchmark that leverages LLMs for automatically identifying root causes, in which we also utilize the proposed taxonomy as guidance for LLMs. Results show that the taxonomy can largely improve the performance, thereby confirming its utility. Nevertheless, the accuracy of root cause identification reaches at most 33.6%, which indicates that this task still remains challenging. In light of these results, we also provide actionable guidelines for building such agentic systems. In summary, this paper provides a reliable dataset of failure root cause for platform-orchestrated agentic systems, corresponding taxonomy and benchmark, which serves as a foundation for advancing the development of more reliable agentic systems.

Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Meta-Tool, a controlled empirical study comparing hypernetwork-based LoRA adaptation against carefully designed few-shot prompting. Using a Llama-3.2-3B-Instruct backbone, we evaluate four adaptation mechanisms--few-shot prompting, documentation encoding, hypernetwork-generated LoRA weights, and value-guided beam search--across four diverse benchmarks: Gorilla APIBench, Spider 2.0, WebArena, and InterCode. Our central finding is a well-supported negative result: despite generating non-trivial weight matrices, the 227.8M-parameter hypernetwork provides no measurable improvement over few-shot prompting alone. Comprehensive ablation studies reveal that few-shot examples contribute +21.5% to performance and documentation contributes +5.0%, while the hypernetwork adds 0%. A 3B model with well-designed prompts achieves 79.7% of GPT-5's average performance at 10 times lower latency. Error analysis across 722 failure cases spanning all shot counts (0--5) shows that at the 5-shot configuration (106 failures), failure modes are task-dependent: schema-heavy tasks (Spider 2.0, WebArena) show near-zero format errors with remaining failures semantic, while format errors dominate on Gorilla (100%) and InterCode (70%). These findings redirect practitioners toward prompt engineering and example curation rather than complex adaptation architectures.

Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes error recognition particularly challenging. Minor errors can propagate across agents, escalating into task failures while producing long, intertwined execution trajectories that impose significant costs for both human developers and automated systems to debug and analyze. Our key insight is that, despite surface differences in failure trajectories (e.g., logs), MAS errors often recur with similar structural patterns. This paper presents CORRECT, the first lightweight, training-free framework that leverages an online cache of distilled error schemata to recognize and transfer knowledge of failure structures across new requests. This cache-based reuse allows LLMs to perform targeted error localization at inference time, avoiding the need for expensive retraining while adapting to dynamic MAS deployments in subseconds. To support rigorous study in this domain, we also introduce CORRECT-Error, a large-scale dataset of over 2,000 annotated trajectories collected through a novel error-injection pipeline guided by real-world distributions, and further validated through human evaluation to ensure alignment with natural failure patterns. Experiments across seven diverse MAS applications show that CORRECT improves step-level error localization up to 19.8% over existing advances while at near-zero overhead, substantially narrowing the gap between automated and human-level error recognition.

Large reasoning models (e.g., R1, o3) have demonstrated remarkable mathematical problem-solving abilities. However, the high reported accuracy of these advanced models on popular datasets, reliance on purely numerical evaluation and potential benchmark leakage, often masks their true reasoning shortcomings. To address this, we propose leveraging the inherent rigor and methodological complexity of mathematical proofs as a diagnostic tool to expose these hidden failures. Specifically, we introduce the RFMDataset (Reveal Failure Modes), a collection of 200 diverse mathematical proof problems, and thoroughly evaluate advanced models' performance on it. Our in-depth analysis of their failures uncovers 10 fine-grained error types, which shows fundamental limitations in current large reasoning models: 1) large reasoning models grapple profoundly with mathematical proofs, with some generating entirely correct proofs for less than 20% of problems and failing even on basic ones; 2) models exhibit a diverse spectrum of reasoning failures, prominently demonstrating the lack of guarantees for the correctness and rigor of single-step reasoning; and 3) models show hallucination and incompleteness during the reasoning process. Our findings reveal that models' self-reflection is insufficient to resolve the current logical dilemmas, necessitating formalized and fine-grained logical training.

In recent years, active learning has been successfully applied to an array of NLP tasks. However, prior work often assumes that training and test data are drawn from the same distribution. This is problematic, as in real-life settings data may stem from several sources of varying relevance and quality. We show that four popular active learning schemes fail to outperform random selection when applied to unlabelled pools comprised of multiple data sources on the task of natural language inference. We reveal that uncertainty-based strategies perform poorly due to the acquisition of collective outliers, i.e., hard-to-learn instances that hamper learning and generalization. When outliers are removed, strategies are found to recover and outperform random baselines. In further analysis, we find that collective outliers vary in form between sources, and show that hard-to-learn data is not always categorically harmful. Lastly, we leverage dataset cartography to introduce difficulty-stratified testing and find that different strategies are affected differently by example learnability and difficulty.

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions, leading to task failure. Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way, and therefore fail to detect these errors accordingly. We address this gap with three contributions. First, we introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations. Second, we construct AgentErrorBench, the first dataset of systematically annotated failure trajectories from ALFWorld, GAIA, and WebShop, grounding error analysis in real-world agent rollouts. Third, we propose AgentDebug, a debugging framework that isolates root-cause failures and provides corrective feedback, enabling agents to recover and iteratively improve. Experiments on AgentErrorBench show that AgentDebug achieves 24% higher all-correct accuracy and 17% higher step accuracy compared to the strongest baseline. Beyond detection, the targeted feedback generated by AgentDebug enables LLM agents to iteratively recover from failures, yielding up to 26% relative improvements in task success across ALFWorld, GAIA, and WebShop. These results establish principled debugging as a pathway to more reliable and adaptive LLM agents. The code and data will be available at https://github.com/ulab-uiuc/AgentDebug

As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a mechanism-centered taxonomy of 41 recurring risk patterns in commercial LLMs. The analysis shows that inputs are often interpreted non-neutrally and can trigger implementation-shaped responses or unintended state changes even without explicit commands. We argue that these behaviors constitute architectural failure modes and that string-level filtering alone is insufficient. To mitigate such cross-stage vulnerabilities, we recommend zero-trust architectural principles, including provenance enforcement, context sealing, and plan revalidation, and we introduce "Countermind" as a conceptual blueprint for implementing these defenses.

With the advent of Transformers, large language models (LLMs) have saturated well-known NLP benchmarks and leaderboards with high aggregate performance. However, many times these models systematically fail on tail data or rare groups not obvious in aggregate evaluation. Identifying such problematic data groups is even more challenging when there are no explicit labels (e.g., ethnicity, gender, etc.) and further compounded for NLP datasets due to the lack of visual features to characterize failure modes (e.g., Asian males, animals indoors, waterbirds on land, etc.). This paper introduces an interactive Systematic Error Analysis and Labeling (\seal) tool that uses a two-step approach to first identify high error slices of data and then, in the second step, introduce methods to give human-understandable semantics to those underperforming slices. We explore a variety of methods for coming up with coherent semantics for the error groups using language models for semantic labeling and a text-to-image model for generating visual features. SEAL toolkit and demo screencast is available at https://huggingface.co/spaces/nazneen/seal.

Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures are typically logged or retried heuristically, they contain structured signals about where execution broke down. We introduce CausalFlow, an interventional framework that converts failed agent traces into minimal counterfactual repairs and reusable supervision. CausalFlow models execution traces as sequential chains of dependent steps and computes Causal Responsibility Scores(CRS) via step-level counterfactual intervention to identify failure-inducing steps. For these steps, we generate minimally edited repairs that flip the final outcome to success, producing validated contrastive pairs of the form (wrong step, corrected step). CausalFlow supports two complementary uses: targeted test-time repair that recovers from failures with minimal behavioral drift, and training-time supervision suitable for offline preference optimization or reward modeling. Across four benchmarks spanning mathematical reasoning, code generation, question answering, and medical browsing, CausalFlow converts failed executions into validated minimal repairs with high minimality and causal-consensus scores, and demonstrates that causal attribution is necessary for reliable improvement across diverse agent tasks, outperforming heuristic refinement in complex retrieval settings while producing more localized repairs throughout. These results demonstrate that interventional analysis over structured execution traces provides a principled and scalable mechanism for transforming agent failures into reliability gains and learning-ready supervision.

Root cause analysis (RCA) is essential for diagnosing failures within complex software systems to ensure system reliability. The highly distributed and interdependent nature of modern cloud-based systems often complicates RCA efforts, particularly for multi-hop fault propagation, where symptoms appear far from their true causes. Recent advancements in Large Language Models (LLMs) present new opportunities to enhance automated RCA. However, their practical value for RCA depends on the fidelity of reasoning and decision-making. Existing work relies on historical incident corpora, operates directly on high-volume telemetry beyond current LLM capacity, or embeds reasoning inside complex multi-agent pipelines -- conditions that obscure whether failures arise from reasoning itself or from peripheral design choices. We present a focused empirical evaluation that isolates an LLM's reasoning behavior. We design a controlled experimental framework that foregrounds the LLM by using a simplified experimental setting. We evaluate six LLMs under two agentic workflows (ReAct and Plan-and-Execute) and a non-agentic baseline on two real-world case studies (GAIA and OpenRCA). In total, we executed 48,000 simulated failure scenarios, totaling 228 days of execution time. We measure both root-cause accuracy and the quality of intermediate reasoning traces. We produce a labeled taxonomy of 16 common RCA reasoning failures and use an LLM-as-a-Judge for annotation. Our results clarify where current open-source LLMs succeed and fail in multi-hop RCA, quantify sensitivity to input data modalities, and identify reasoning failures that predict final correctness. Together, these contributions provide transparent and reproducible empirical results and a failure taxonomy to guide future work on reasoning-driven system diagnosis.

As Large Language Models (LLMs) are deployed with increasing real-world responsibilities, it is important to be able to specify and constrain the behavior of these systems in a reliable manner. Model developers may wish to set explicit rules for the model, such as "do not generate abusive content", but these may be circumvented by jailbreaking techniques. Evaluating how well LLMs follow developer-provided rules in the face of adversarial inputs typically requires manual review, which slows down monitoring and methods development. To address this issue, we propose Rule-following Language Evaluation Scenarios (RuLES), a programmatic framework for measuring rule-following ability in LLMs. RuLES consists of 15 simple text scenarios in which the model is instructed to obey a set of rules in natural language while interacting with the human user. Each scenario has a concise evaluation program to determine whether the model has broken any rules in a conversation. Through manual exploration of model behavior in our scenarios, we identify 6 categories of attack strategies and collect two suites of test cases: one consisting of unique conversations from manual testing and one that systematically implements strategies from the 6 categories. Across various popular proprietary and open models such as GPT-4 and Llama 2, we find that all models are susceptible to a wide variety of adversarial hand-crafted user inputs, though GPT-4 is the best-performing model. Additionally, we evaluate open models under gradient-based attacks and find significant vulnerabilities. We propose RuLES as a challenging new setting for research into exploring and defending against both manual and automatic attacks on LLMs.

Benchmarks are important tools to track progress in the development of Large Language Models (LLMs), yet inaccuracies in datasets and evaluation methods consistently undermine their effectiveness. Here, we present Omni-MATH-2, a manually revised version of the Omni-MATH dataset comprising a clean, exact-answer subset (n{=}4181) and a tagged, non-standard subset (n{=}247). Each problem was audited to ensure LaTeX compilability, solvability and verifiability, which involved adding missing figures or information, labeling problems requiring a proof, estimation or image, and removing clutter. This process significantly reduces dataset-induced noise, thereby providing a more precise assessment of model performance. The annotated dataset also allows us to evaluate judge-induced noise by comparing GPT-5 mini with the original Omni-Judge, revealing substantial discrepancies between judges on both the clean and tagged problem subsets. Expert annotations reveal that Omni-Judge is wrong in 96.4% of the judge disagreements, indicating its inability to differentiate between models' abilities, even well before saturation of the benchmark occurs. As problems become more challenging, we find that increasingly competent judges become essential in order to prevent judge errors from masking genuine differences between models. Finally, neither judge identifies the present failure modes for the subset of tagged problems, demonstrating that dataset quality and judge reliability are both critical to develop accurate benchmarks of model performance.

Large Language Models (LLMs) have shown tremendous potential as agents, excelling at tasks that require multiple rounds of reasoning and interactions. Rejection Sampling Fine-Tuning (RFT) has emerged as an effective method for finetuning LLMs as agents: it first imitates expert-generated successful trajectories and further improves agentic skills through iterative fine-tuning on successful, self-generated trajectories. However, since the expert (e.g., GPT-4) succeeds primarily on simpler subtasks and RFT inherently favors simpler scenarios, many complex subtasks remain unsolved and persistently out-of-distribution (OOD). Upon investigating these challenging subtasks, we discovered that previously failed expert trajectories can often provide valuable guidance, e.g., plans and key actions, that can significantly improve agent exploration efficiency and acquisition of critical skills. Motivated by these observations, we propose Exploring Expert Failures (EEF), which identifies beneficial actions from failed expert trajectories and integrates them into the training dataset. Potentially harmful actions are meticulously excluded to prevent contamination of the model learning process. By leveraging the beneficial actions in expert failures, EEF successfully solves some previously unsolvable subtasks and improves agent tuning performance. Remarkably, our approach achieved a 62\% win rate in WebShop, outperforming RFT (53. 6\%) and GPT-4 (35. 6\%), and to the best of our knowledge, setting a new state-of-the-art as the first method to surpass a score of 0.81 in WebShop and exceed 81 in SciWorld.

Since large language models have approached human-level performance on many tasks, it has become increasingly harder for researchers to find tasks that are still challenging to the models. Failure cases usually come from the long-tail distribution - data that an oracle language model could assign a probability on the lower end of its distribution. Current methodology such as prompt engineering or crowdsourcing are insufficient for creating long-tail examples because humans are constrained by cognitive bias. We propose a Logic-Induced-Knowledge-Search (LINK) framework for systematically generating long-tail knowledge statements. Grounded by a symbolic rule, we search for long-tail values for each variable of the rule by first prompting a LLM, then verifying the correctness of the values with a critic, and lastly pushing for the long-tail distribution with a reranker. With this framework we construct a dataset, Logic-Induced-Long-Tail (LINT), consisting of 200 symbolic rules and 50K knowledge statements spanning across four domains. Human annotations find that 84% of the statements in LINT are factually correct. In contrast, ChatGPT and GPT4 struggle with directly generating long-tail statements under the guidance of logic rules, each only getting 56% and 78% of their statements correct. Moreover, their "long-tail" generations in fact fall into the higher likelihood range, and thus are not really long-tail. Our findings suggest that LINK is effective for generating data in the long-tail distribution while enforcing quality. LINT can be useful for systematically evaluating LLMs' capabilities in the long-tail distribution. We challenge the models with a simple entailment classification task using samples from LINT. We find that ChatGPT and GPT4's capability in identifying incorrect knowledge drop by ~3% in the long-tail distribution compared to head distribution.

Software engineers develop, fine-tune, and deploy deep learning (DL) models. They use and re-use models in a variety of development frameworks and deploy them on a range of runtime environments. In this diverse ecosystem, engineers use DL model converters to move models from frameworks to runtime environments. However, errors in converters can compromise model quality and disrupt deployment. The failure frequency and failure modes of DL model converters are unknown. In this paper, we conduct the first failure analysis on DL model converters. Specifically, we characterize failures in model converters associated with ONNX (Open Neural Network eXchange). We analyze past failures in the ONNX converters in two major DL frameworks, PyTorch and TensorFlow. The symptoms, causes, and locations of failures (for N=200 issues), and trends over time are also reported. We also evaluate present-day failures by converting 8,797 models, both real-world and synthetically generated instances. The consistent result from both parts of the study is that DL model converters commonly fail by producing models that exhibit incorrect behavior: 33% of past failures and 8% of converted models fell into this category. Our results motivate future research on making DL software simpler to maintain, extend, and validate.

Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic systems, these long-horizon failures remain poorly characterized, hindering principled diagnosis and comparison across domains. To address this gap, we introduce HORIZON, an initial cross-domain diagnostic benchmark for systematically constructing tasks and analyzing long-horizon failure behaviors in LLM-based agents. Using HORIZON, we evaluate state-of-the-art (SOTA) agents from multiple model families (GPT-5 variants and Claude models), collecting 3100+ trajectories across four representative agentic domains to study horizon-dependent degradation patterns. We further propose a trajectory-grounded LLM-as-a-Judge pipeline for scalable and reproducible failure attribution, and validate it with human annotation on trajectories, achieving strong agreement (inter-annotator κ=0.61; human-judge κ=0.84). Our findings offer an initial methodological step toward systematic, cross-domain analysis of long-horizon agent failures and offer practical guidance for building more reliable long-horizon agents. We release our project website at https://xwang2775.github.io/horizon-leaderboard/{HORIZON Leaderboard} and welcome contributions from the community.

This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. Unlike prior studies that focus solely on answer correctness, we rigorously analyze both final answers and solution steps to identify reasoning failures. Evaluating eight state-of-the-art models - including Mixtral, Llama, Gemini, GPT-4o, and OpenAI's o1 variants - we find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic, sometimes producing correct answers through flawed logic. Common failure modes include unwarranted assumptions, over-reliance on numerical patterns, and difficulty translating physical intuition into mathematical steps. Manual analysis reveals that models struggle with problems requiring multi-step deduction or real-world knowledge, despite possessing broad mathematical knowledge. Our results underscore the importance of evaluating reasoning processes, not just answers, and caution against overestimating LLMs' problem-solving proficiency. The study highlights persistent gaps in LLMs' generalization abilities, emphasizing the need for targeted improvements in structured reasoning and constraint handling.

Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint. We study this through a diagnose-measure-bridge-treat framework. Causal-behavioral analysis of the ``car wash problem'' across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the goal, and token-level attribution shows patterns more consistent with keyword associations than compositional inference. The Heuristic Override Benchmark (HOB) -- 500 instances spanning 4 heuristic by 5 constraint families with minimal pairs and explicitness gradients -- demonstrates generality across 14 models: under strict evaluation (10/10 correct), no model exceeds 75%, and presence constraints are hardest (44%). A minimal hint (e.g., emphasizing the key object) recovers +15 pp on average, suggesting the failure lies in constraint inference rather than missing knowledge; 12/14 models perform worse when the constraint is removed (up to -39 pp), revealing conservative bias. Parametric probes confirm that the sigmoid pattern generalizes to cost, efficiency, and semantic-similarity heuristics; goal-decomposition prompting recovers +6 to 9 pp by forcing models to enumerate preconditions before answering. Together, these results characterize heuristic override as a systematic reasoning vulnerability and provide a benchmark for measuring progress toward resolving it.

Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such as direct prediction of agent-error pairs and agent-first failure attribution, rely on local logs of agents and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-grained attribution. To address these challenges, we propose VerifyMAS, a hypothesis verification framework for agent failure attribution. Instead of directly predicting faulty agents and error types, VerifyMAS formulates and verifies failure hypotheses against full trajectories. This verification-based approach decomposes attribution into trajectory-level error validation and fine-grained agent localization, providing an error-first attribution approach that captures global failure patterns while substantially reducing the search space. We further introduce a hypothesis-based data construction strategy grounded in a structured error taxonomy and fine-tune a specialized LLM verifier model for trajectory-level failure verification and agent attribution. Experiments on Aegis-Bench and Who&When show that VerifyMAS consistently improves diverse backbone models, including open-source Qwen and API-based GPT models, outperforming prior methods without sacrificing inference efficiency for long multi-agent trajectories.

As Multi-Agent Systems (MAS) become increasingly autonomous and complex, understanding their error modes is critical for ensuring their reliability and safety. However, research in this area has been severely hampered by the lack of large-scale, diverse datasets with precise, ground-truth error labels. To address this bottleneck, we introduce AEGIS, a novel framework for Automated Error Generation and Identification for Multi-Agent Systems. By systematically injecting controllable and traceable errors into initially successful trajectories, we create a rich dataset of realistic failures. This is achieved using a context-aware, LLM-based adaptive manipulator that performs sophisticated attacks like prompt injection and response corruption to induce specific, predefined error modes. We demonstrate the value of our dataset by exploring three distinct learning paradigms for the error identification task: Supervised Fine-Tuning, Reinforcement Learning, and Contrastive Learning. Our comprehensive experiments show that models trained on AEGIS data achieve substantial improvements across all three learning paradigms. Notably, several of our fine-tuned models demonstrate performance competitive with or superior to proprietary systems an order of magnitude larger, validating our automated data generation framework as a crucial resource for developing more robust and interpretable multi-agent systems. Our project website is available at https://kfq20.github.io/AEGIS-Website.

Large language models (LLMs) have shown incredible performance in completing various real-world tasks. The current knowledge learning paradigm of LLMs is mainly based on learning from examples, in which LLMs learn the internal rule implicitly from a certain number of supervised examples. However, this learning paradigm may not well learn those complicated rules, especially when the training examples are limited. We are inspired that humans can learn the new tasks or knowledge in another way by learning from rules. That is, humans can learn new tasks or grasps new knowledge quickly and generalize well given only a detailed rule and a few optional examples. Therefore, in this paper, we aim to explore the feasibility of this new learning paradigm, which targets on encoding rule-based knowledge into LLMs. We further propose rule distillation, which first uses the strong in-context abilities of LLMs to extract the knowledge from the textual rules, and then explicitly encode the knowledge into the parameters of LLMs by learning from the above in-context signals produced inside the model. Our experiments show that making LLMs learn from rules by our method is much more efficient than example-based learning in both the sample size and generalization ability. Warning: This paper may contain examples with offensive content.

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.

Can a mere next-token predictor faithfully model human intelligence? We crystallize this intuitive concern, which is fragmented in the literature. As a starting point, we argue that the two often-conflated phases of next-token prediction -- autoregressive inference and teacher-forced training -- must be treated distinctly. The popular criticism that errors can compound during autoregressive inference, crucially assumes that teacher-forcing has learned an accurate next-token predictor. This assumption sidesteps a more deep-rooted problem we expose: in certain classes of tasks, teacher-forcing can simply fail to learn an accurate next-token predictor in the first place. We describe a general mechanism of how teacher-forcing can fail, and design a minimal planning task where both the Transformer and the Mamba architecture empirically fail in that manner -- remarkably, despite the task being straightforward to learn. We provide preliminary evidence that this failure can be resolved when training to predict multiple tokens in advance. We hope this finding can ground future debates and inspire explorations beyond the next-token prediction paradigm. We make our code available under https://github.com/gregorbachmann/Next-Token-Failures

Large language models (LLMs) can call tools effectively, yet they remain brittle in multi-turn execution: following a tool call error, smaller models often degenerate into repetitive invalid re-invocations, failing to interpret error feedback and self-correct. This brittleness hinders reliable real-world deployment, where the execution errors are inherently inevitable during tool interaction procedures. We identify a key limitation of current approaches: standard reinforcement learning (RL) treats errors as sparse negative rewards, providing no guidance on how to recover, while pre-collected synthetic error-correction datasets suffer from distribution mismatch with the model's on-policy error modes. To bridge this gap, we propose Fission-GRPO, a framework that converts execution errors into corrective supervision within the RL training loop. Our core mechanism fissions each failed trajectory into a new training instance by augmenting it with diagnostic feedback from a finetuned Error Simulator, then resampling recovery rollouts on-policy. This enables the model to learn from the precise errors it makes during exploration, rather than from static, pre-collected error cases. On the BFCL v4 Multi-Turn, Fission-GRPO improves the error recovery rate of Qwen3-8B by 5.7% absolute, crucially, yielding a 4% overall accuracy gain (42.75% to 46.75%) over GRPO and outperforming specialized tool-use agents.

Large language models perform strongly on benchmarks in mathematical reasoning, coding and document analysis, suggesting a broad ability to follow instructions. However, it remains unclear whether such success reflects general logical competence, repeated application of learned procedures, or pattern matching that mimics rule execution. We investigate this question by introducing Stable Counting Capacity, an assay in which models count repeated symbols until failure. The assay removes knowledge dependencies, semantics and ambiguity from evaluation, avoids lexical and tokenization confounds, and provides a direct measure of procedural reliability beyond standard knowledge-based benchmarks. Here we show, across more than 100 model variants, that stable counting capacity remains far below advertised context limits. Model behavior is consistent neither with open-ended logic nor with stable application of a learned rule, but instead with use of a finite set of count-like internal states, analogous to counting on fingers. Once this resource is exhausted, the appearance of rule following disappears and exact execution collapses into guessing, even with additional test-time compute. These findings show that fluent performance in current language models does not guarantee general, reliable rule following.

Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge of adaptive replanning under spatio-temporal dynamics largely unexplored. We introduce STT-Arena (Spatio-Temporal Tool-Use Arena), a benchmark of 227 high-quality interactive tasks spanning nine spatio-temporal conflict types and four solvability levels. Each task is grounded in a realistic, executable environment equipped with injected spatio-temporal triggers that can abruptly invalidate an ongoing plan, forcing the model to detect the state shift and construct a revised execution strategy. Extensive evaluation of frontier LLMs reveals that even the SOTA proprietary models, including Claude-4.6-Opus, achieves less than 40\% overall accuracies, highlighting the fundamental difficulty of spatio-temporal dynamic reasoning. Systematic analysis of failure trajectories uncovers three recurring error modes of existing models: Stale-State Execution, Misdiagnosis of Dynamic Triggers, and Missing Post-Adaptation Verification. Guided by these findings, we propose an iterative trajectory refinement technique that eliminates these failure patterns from training data, and combine it with online RL to produce STT-Agent-4B which outperforms frontier LLMs on STT-Arena.

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, with refusal accuracy dropping below 50% on multi-document tasks, while exhibiting either dangerous overconfidence or overcaution. Static benchmarks fail to reliably evaluate this capability, as models exploit dataset-specific artifacts and memorize test instances. We introduce RefusalBench, a generative methodology that programmatically creates diagnostic test cases through controlled linguistic perturbation. Our framework employs 176 distinct perturbation strategies across six categories of informational uncertainty and three intensity levels. Evaluation of over 30 models uncovers systematic failure patterns: refusal comprises separable detection and categorization skills, and neither scale nor extended reasoning improves performance. We find that selective refusal is a trainable, alignment-sensitive capability, offering a clear path for improvement. We release two benchmarks -- RefusalBench-NQ (single document) and RefusalBench-GaRAGe (multi-document) -- and our complete generation framework to enable continued, dynamic evaluation of this critical capability.

One of the main challenges developers face in the use of continuous integration (CI) and deployment pipelines is the occurrence of intermittent job failures, which result from unexpected non-deterministic issues (e.g., flaky tests or infrastructure problems) rather than regular code-related errors such as bugs. Prior studies developed machine learning (ML) models trained on large datasets of job logs to classify job failures as either intermittent or regular. As an alternative to costly manual labeling of large datasets, the state-of-the-art (SOTA) approach leveraged a heuristic based on non-deterministic job reruns. However, this method mislabels intermittent job failures as regular in contexts where rerunning suspicious job failures is not an explicit policy, and therefore limits the SOTA's performance in practice. In fact, our manual analysis of 2,125 job failures from 5 industrial and 1 open-source projects reveals that, on average, 32% of intermittent job failures are mislabeled as regular. To address these limitations, this paper introduces a novel approach to intermittent job failure detection using few-shot learning (FSL). Specifically, we fine-tune a small language model using a few number of manually labeled log examples to generate rich embeddings, which are then used to train an ML classifier. Our FSL-based approach achieves 70-88% F1-score with only 12 shots in all projects, outperforming the SOTA, which proved ineffective (34-52% F1-score) in 4 projects. Overall, this study underlines the importance of data quality over quantity and provides a more efficient and practical framework for the detection of intermittent job failures in organizations.

Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing constraints on a neural model during training. However, such work assumes the existence of such constraints a-priori. In this paper, we relax this strong assumption and present an approach based on Error Detection Rules (EDR) that allow for learning explainable rules about the failure modes of machine learning models. We show that these rules are not only effective in detecting when a machine learning classifier has made an error but also can be leveraged as constraints for HMC, thereby allowing the recovery of explainable constraints even if they are not provided. We show that our approach is effective in detecting machine learning errors and recovering constraints, is noise tolerant, and can function as a source of knowledge for neurosymbolic models on multiple datasets, including a newly introduced military vehicle recognition dataset.

A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural guidance -- together implying a monotone inverse relationship between model capability tier and optimal harness complexity. We test this hypothesis through a controlled 432-run experiment crossing six models across four capability tiers with three harness conditions (light, balanced, strict) on HEAT-24, a 24-task synthetic benchmark with git-based workspace verification. Our results refute the monotone inverse relationship on two fronts. First, for the frontier chat model evaluated (Gemini 2.5 Flash), increased harness verbosity lowers VTSR by 29-38 percentage points -- a harness-complexity paradox. Second, for the frontier reasoning model evaluated (Qwen3.5-122B, extended thinking enabled), strict harness achieves the highest VTSR (91.7%) and the lowest latency, the opposite of the prediction. Within the constrained tier, a 2B model (Gemma4:e2B) matches strong-open-tier stability at 91.7% across all harnesses. Because each tier is represented by a single model in this study, these results should be interpreted as model-specific observations; harness sensitivity appears non-monotone across the models evaluated, and depends critically on model type (chat vs. reasoning). We introduce a six-label failure taxonomy showing that format_violation dominates capable-model failures while wrong_file dominates low-capability failures, and we derive practical tier-aware harness selection guidelines.

Rule-based reasoning has been acknowledged as one of the fundamental problems in reasoning, while deviations in rule formats, types, and complexity in real-world applications pose severe challenges. Recent studies have shown that large reasoning models (LRMs) have remarkable reasoning capabilities, and their performance is substantially enhanced by reinforcement learning (RL). However, it remains an open question whether small reasoning models (SRMs) can learn rule-based reasoning effectively with robust generalization across diverse tasks and domains. To address this, we introduce Reinforced Rule-based Reasoning, a.k.a. RuleReasoner, a simple yet effective method to conduct rule-based reasoning via a wide collection of curated tasks and a novel domain-aware dynamic sampling approach. Specifically, RuleReasoner resamples each training batch by updating the sampling weights of different domains based on historical rewards. This facilitates domain augmentation and flexible online learning schedules for RL, obviating the need for pre-hoc human-engineered mix-training recipes used in existing methods. Empirical evaluations on in-distribution (ID) and out-of-distribution (OOD) benchmarks reveal that RuleReasoner outperforms frontier LRMs by a significant margin (Delta4.1% average points on eight ID tasks and Delta10.4% average points on three OOD tasks over OpenAI-o1). Notably, our approach also exhibits higher computational efficiency compared to prior dynamic sampling methods for RL.

Despite advances in large language models (LLMs) on reasoning and instruction-following benchmarks, it remains unclear whether they can reliably produce outputs aligned with a broad variety of user goals, a concept we refer to as steerability. The abundance of methods proposed to modify LLM behavior makes it unclear whether current LLMs are already steerable, or require further intervention. In particular, LLMs may exhibit (i) poor coverage, where rare user goals are underrepresented; (ii) miscalibration, where models overshoot requests; and (iii) side effects, where changes to one dimension of text inadvertently affect others. To systematically evaluate these failures, we introduce a framework based on a multi-dimensional goal space that models user goals and LLM outputs as vectors with dimensions corresponding to text attributes (e.g., reading difficulty). Applied to a text-rewriting task, we find that current LLMs struggle with steerability, as side effects are persistent. Interventions to improve steerability, such as prompt engineering, best-of-N sampling, and reinforcement learning fine-tuning, have varying effectiveness, yet side effects remain problematic. Our findings suggest that even strong LLMs struggle with steerability, and existing alignment strategies may be insufficient. We open-source our steerability evaluation framework at https://github.com/MLD3/steerability.

Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that they can successfully solve. Such observations motivate us to propose methods that encourage models to understand the high-level and abstract reasoning processes during training instead of only the final answer. This way, models can transfer the exact solution to similar cases, regardless of their relevance to the pre-training data distribution. In this work, we propose SAL, a self-supervised analogical learning framework. SAL mimics the human analogy process and trains models to explicitly transfer high-quality symbolic solutions from cases that they know how to solve to other rare cases in which they tend to fail more. We show that the resulting models after SAL learning outperform base language models on a wide range of reasoning benchmarks, such as StrategyQA, GSM8K, and HotpotQA, by 2% to 20%. At the same time, we show that our model is more generalizable and controllable through analytical studies.

RAG (Retrieval-Augmented Generation) systems and web agents are increasingly evaluated on multi-hop deep search tasks, yet current practice suffers from two major limitations. First, most benchmarks leak the reasoning path in the question text, allowing models to follow surface cues rather than discover reasoning chains autonomously. Second, evaluation is typically reduced to a single pass rate, which collapses diverse behaviours into one score and obscures whether failures stem from inadequate search, poor knowledge use, or inappropriate refusal. To address these issues, we present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox that ensures full traceability of model actions, and a holistic evaluation framework that separates search sufficiency, knowledge utilisation, and refusal behaviour. Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures: models struggle with knowledge utilisation despite having sufficient evidence and demonstrate near-absent appropriate refusal when evidence is lacking. These patterns expose a fundamental gap: today's systems excel at executing given reasoning paths but fail when required to discover them. We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies, incorporating verification loops and systematic evidence tracking that improve both search and synthesis capabilities. This baseline demonstrates that WebDetective's diagnostic framework can guide concrete architectural improvements, establishing our benchmark as a critical tool for developing genuinely autonomous reasoning systems rather than pattern-following agents.

As language model agents are applied to real world problems of increasing complexity, they will be expected to formulate plans across large search spaces. If those plans fail for reasons beyond their control, how well do language agents search for alternative ways to achieve their goals? We devise a specialized agentic planning benchmark to study this question. Each planning problem is solved via combinations of function calls. The agent searches for relevant functions from a set of over four thousand possibilities, and observes environmental feedback in the form of function outputs or error messages. Our benchmark confronts the agent with external failures in its workflow, such as functions that suddenly become unavailable. At the same time, even with the introduction of these failures, we guarantee that the task remains solvable. Ideally, an agent's performance on the planning task should not be affected by the presence of external failures. Overall, we find that language agents struggle to formulate and execute backup plans in response to environment feedback. While state-of-the-art models are often able to identify the correct function to use in the right context, they struggle to adapt to feedback from the environment and often fail to pursue alternate courses of action, even when the search space is artificially restricted. We provide a systematic analysis of the failures of both open-source and commercial models, examining the effects of search space size, as well as the benefits of scaling model size in our setting. Our analysis identifies key challenges for current generative models as well as promising directions for future work.

Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the label. We show that generative classifiers, which use class-conditional generative models, can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones. These generative classifiers are simple to train, avoiding the need for specialized augmentations, strong regularization, extra hyperparameters, or knowledge of the specific spurious correlations to avoid. We find that diffusion-based and autoregressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks and reduce the impact of spurious correlations in realistic applications, such as medical or satellite datasets. Finally, we carefully analyze a Gaussian toy setting to understand the inductive biases of generative classifiers, as well as the data properties that determine when generative classifiers outperform discriminative ones.

Despite growing enthusiasm for Multi-Agent Systems (MAS), where multiple LLM agents collaborate to accomplish tasks, their performance gains across popular benchmarks remain minimal compared to single-agent frameworks. This gap highlights the need to analyze the challenges hindering MAS effectiveness. In this paper, we present the first comprehensive study of MAS challenges. We analyze five popular MAS frameworks across over 150 tasks, involving six expert human annotators. We identify 14 unique failure modes and propose a comprehensive taxonomy applicable to various MAS frameworks. This taxonomy emerges iteratively from agreements among three expert annotators per study, achieving a Cohen's Kappa score of 0.88. These fine-grained failure modes are organized into 3 categories, (i) specification and system design failures, (ii) inter-agent misalignment, and (iii) task verification and termination. To support scalable evaluation, we integrate MASFT with LLM-as-a-Judge. We also explore if identified failures could be easily prevented by proposing two interventions: improved specification of agent roles and enhanced orchestration strategies. Our findings reveal that identified failures require more complex solutions, highlighting a clear roadmap for future research. We open-source our dataset and LLM annotator.

Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesigned environments between stages, requiring practitioners to heuristically infer which configuration will best improve the current policy. To automate this process, we propose the LLM-as-Environment-Engineer framework in which the current policy model analyzes failure trajectories together with contextual information and proposes modifications to the next-stage training environment configuration. We also introduce MAPF-FrozenLake, a controllable testbed whose generator exposes multi-dimensional environment configurations, making it suitable for studying and benchmarking environment redesign. On this testbed, we condition the environment engineer on structured summaries of policy behavior, failure cases, and environment statistics, from which it produces the configuration for the next training stage. With Qwen3-4B as the backbone, our framework achieves the strongest aggregate performance on our benchmarks, outperforming larger proprietary LLMs (e.g., GPT, Gemini) and fixed-environment training baselines. We further analyze which forms of context are most effective, finding that successful environment updates rely on failure evidence and preserve configurations that already work. Interestingly, the current RL checkpoint serves as a better environment engineer than the original base model, suggesting that policy learning improves the model's ability to diagnose its remaining weaknesses.

How do multi-turn reasoning systems fail? The expected answer is logical contradiction, in which the system's maintained state becomes unsatisfiable. We show that the dominant mode is instead satisfiable drift, where the internal state stays consistent while the returned answer silently violates prior commitments. We build DRIFT-Bench (Decomposing Reasoning Into Failure Types), a solver-instrumented benchmark of 816 test problems across three constraint domains, and evaluate four methods on it across four open-weight models (8B-120B parameters). MUS-Repair, which feeds minimal unsatisfiable subsets back to the generator, is strongest in every setting (+1.8 to +15.0 pp over the best non-MUS baseline). But the central finding is what repair leaves behind. After structured feedback, models rarely contradict themselves. They forget. Residual errors are 98-100% satisfiable drift across all settings, while contradiction drops to near zero. Reliable multi-turn systems must separately validate that the returned answer respects the maintained state. Code is available at https://github.com/kaons-research/drift-bench.

Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-based pipelines, which are computationally expensive, or require post-training on failure trajectories with step-level error annotations, which are costly to collect and difficult to scale. We argue that a practical failure attribution model should be lightweight and trainable without step-level supervision on failure data. To this end, we address unsupervised failure attribution, i.e., training exclusively on successful trajectories and identifying error steps at inference time given a failure trajectory. We propose OAT, which casts this problem as one-class learning with neural controlled differential equations, modeling the dynamical pattern of successful trajectories in latent space. At inference time, each step in a failure trajectory is assigned an anomaly score based on its deviation from the dynamics learned on successful trajectories, which is then used to form a set of error steps. With training on only 100 successful trajectories, experiments show that OAT is 200--5000 times faster than prompting-based baselines, and, at the same time, consistently outperforms them in both in-domain and out-of-distribution datasets with +20% and +7% F1 scores, respectively, demonstrating that OAT is a promising and efficient direction for diagnosing agentic system failures.

Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers and complete tasks, have attracted significant attention for their utility and versatility. A major challenge in developing these agents is collecting large-scale, high-quality trajectories. The standard approach generates synthetic data through a self-improving loop: an agent is placed in a verifiable environment and iteratively fine-tuned on its successful trajectories. Despite its effectiveness, this paradigm exploits only successful trajectories and discards the failed ones, even though failures carry rich information about a model's weaknesses. In this work, we explore a complementary failure-driven self-improvement loop, a data-centric paradigm that turns failed trajectories into agent improvements. Specifically, we employ an LLM to diagnose failure modes, propose inference-time solutions, and generate code patches -- lightly verified by humans -- that upgrade the agent. We validate this approach with the state-of-the-art OpenCUA-72B model on the OSWorld benchmark, improving the success rate from 42.3% to 48.9%, a gain of 6.6 percentage points, without any additional training cost and with only modest inference overhead. Our results demonstrate that failure-driven self-improvement is a viable complement to success-based pipelines, enabling more efficient agent improvement.

Recent advances in robotic manipulation have integrated low-level robotic control into Vision-Language Models (VLMs), extending them into Vision-Language-Action (VLA) models. Although state-of-the-art VLAs achieve strong performance in downstream robotic applications, supported by large-scale crowd-sourced robot training data, they still inevitably encounter failures during execution. Enabling robots to reason and recover from unpredictable and abrupt failures remains a critical challenge. Existing robotic manipulation datasets, collected in either simulation or the real world, primarily provide only ground-truth trajectories, leaving robots unable to recover once failures occur. Moreover, the few datasets that address failure detection typically offer only textual explanations, which are difficult to utilize directly in VLA models. To address this gap, we introduce FailSafe, a novel failure generation and recovery system that automatically produces diverse failure cases paired with executable recovery actions. FailSafe can be seamlessly applied to any manipulation task in any simulator, enabling scalable creation of failure action data. To demonstrate its effectiveness, we fine-tune LLaVa-OneVision-7B (LLaVa-OV-7B) to build FailSafe-VLM. Experimental results show that FailSafe-VLM successfully helps robotic arms detect and recover from potential failures, improving the performance of three state-of-the-art VLA models (pi0-FAST, OpenVLA, OpenVLA-OFT) by up to 22.6% on average across several tasks in Maniskill. Furthermore, FailSafe-VLM could generalize across different spatial configurations, camera viewpoints, object and robotic embodiments. We plan to release the FailSafe code to the community.

The impressive performance of Large Language Models (LLMs) has consistently surpassed numerous human-designed benchmarks, presenting new challenges in assessing the shortcomings of LLMs. Designing tasks and finding LLMs' limitations are becoming increasingly important. In this paper, we investigate the question of whether an LLM can discover its own limitations from the errors it makes. To this end, we propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances and incorporate human feedback on them to refine these patterns for generating more challenging data, iteratively. We end up with 8 diverse patterns, such as text manipulation and questions with assumptions. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses. The SC-G4 serves as a challenging benchmark that allows for a detailed assessment of LLMs' abilities. Our results show that only 44.96\% of instances in SC-G4 can be answered correctly by GPT-4. Interestingly, our pilot study indicates that these error patterns also challenge other LLMs, such as Claude-3 and Llama-3, and cannot be fully resolved through fine-tuning. Our work takes the first step to demonstrate that LLMs can autonomously identify their inherent flaws and provide insights for future dynamic and automatic evaluation.

AI systems fail silently far more often than they fail visibly. In an analysis of 100K human-AI interactions from the WildChat dataset, we find that 79% of AI failures are invisible: something went wrong but the user gave no overt indication that there was a problem. These invisible failures cluster into eight archetypes that help us characterize where and how AI systems are failing to meet users' needs. In addition, the archetypes show systematic co-occurrence patterns indicating higher-level failure types. To address the question of whether these archetypes will remain relevant as AI systems become more capable, we also created and annotated a counterfactual dataset in which WildChat's 2024-era responses are replaced by those from three present-day frontier LMs. This analysis indicates that failure rates have dropped substantially, but that the vast majority of failures remain invisible in our sense, and the distribution of failure archetypes seems stable. Finally, we illustrate how the archetypes help us to identify systematic and variable AI limitations across different usage domains. Overall, we argue that our invisible failure taxonomy can be a key component in reliable failure monitoring for product developers, scientists, and policy makers. Our code and data are available at https://github.com/bigspinai/bigspin-invisible-failure-archetypes

Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix. This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking, overt jailbreak, and a distinct failure mode we term context-injection failure (where the CoT maintains safe reasoning, but the visible output produces harm, highlighting a multi-turn manifestation of reasoning unfaithfulness). We evaluate three distilled reasoning targets against a fixed attacker across five oversight conditions, collecting 6750 turn-level observations on the Information-Hazard scenario. Our analysis reveals two reproducible vulnerabilities: an oversight paradox where explicit monitoring cues paradoxically increase alignment-faking rates rather than suppress them, and a context-injection failure where models lock onto unsafe external outputs despite safe internal states. We release the full dataset of multi-turn dialogues and CoT traces to support follow-up trace-diagnostic research.

Large language models (LLMs) struggle with multi-step reasoning, where inference-time scaling has emerged as a promising strategy for performance improvement. Verifier-guided search outperforms repeated sampling when sample size is limited by selecting and prioritizing valid reasoning paths. However, we identify a critical limitation: scaling flaws, prevalent across different models (Mistral 7B and DeepSeekMath 7B), benchmarks (GSM8K and MATH), and verifiers (outcome value models and process reward models). As sample size increases, verifier-guided search exhibits diminishing advantages and eventually underperforms repeated sampling. Our analysis attributes this to verifier failures, where imperfect verifiers misrank candidates and erroneously prune all valid paths. These issues are further exacerbated in challenging and out-of-distribution problems, restricting search effectiveness. To mitigate verifier failures, we explore reducing reliance on verifiers and conduct preliminary investigations using two simple methods. Our findings reveal fundamental limitations in verifier-guided search and suggest future directions.

Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm has two key limitations: (i) log-only debugging lacks validation, producing untested hypotheses, and (ii) single-step or single-agent attribution is often ill-posed, as we find that multiple distinct interventions can independently repair the failed task. To address the first limitation, we introduce DoVer, an intervention-driven debugging framework, which augments hypothesis generation with active verification through targeted interventions (e.g., editing messages, altering plans). For the second limitation, rather than evaluating on attribution accuracy, we focus on measuring whether the system resolves the failure or makes quantifiable progress toward task success, reflecting a more outcome-oriented view of debugging. Within the Magnetic-One agent framework, on the datasets derived from GAIA and AssistantBench, DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses. DoVer also performs effectively on a different dataset (GSMPlus) and agent framework (AG2), where it recovers 49% of failed trials. These results highlight intervention as a practical mechanism for improving reliability in agentic systems and open opportunities for more robust, scalable debugging methods for LLM-based multi-agent systems. Project website and code will be available at https://aka.ms/DoVer.

Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history. We show that an event-sourced agent runtime removes that friction and turns controlled improvement into a first-class workflow. When the agent's state is a deterministic projection of an append-only event log, failures are recorded, a run replays exactly from its log, candidate patches scope to typed pipeline seams, gates are auditable, and every promotion or discard is itself an event. We demonstrate this with Regimes, a loop on the ActiveGraph runtime that diagnoses failed evaluations, proposes a repair at a pipeline point, and promotes it only after static checks, sandbox execution, in-sample evaluation, and held-out validation. The loop is target-agnostic: the same control flow runs against different tasks through a common interface. On LongMemEval-S the dominant failure is not retrieval but reconciliation: the evidence is already in the assembled context, yet the reader answers incorrectly. Across five seeded held-out splits, Regimes discovers reader-prompt repairs that improve final held-out accuracy by +0.05 to +0.10 in four splits and +0.01 in one over-promotion split; two splits are individually significant (seed 5 unadjusted for its sequential promotion structure), and the pooled count is descriptive only, since the splits share one 500-question pool. The durable contributions are ActiveGraph as an auditable substrate that makes controlled improvement loops tractable, the held-out-gated loop it supports, the failure-regime taxonomy routing each failure to a pipeline location (whose marginal value over an unrouted baseline is the primary open question), and the prompt-as-discovery-probe hypothesis.

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

Reliably transferring specialized human knowledge from text into large language models remains a fundamental challenge in artificial intelligence. Fine-tuning on domain corpora has enabled substantial capability gains, but the process operates without feedback: when a model fails on a domain task, there is no method to diagnose what is deficient in the training data, and the only recourse is to add more data indiscriminately. Here we show that when a structured knowledge representation extracted from the source corpus serves as the shared foundation for both training data and evaluation, the complete data-engineering lifecycle maps onto the software development lifecycle in a precise and operative way: training data becomes source code specifying what the model should learn, model training becomes compilation, benchmarking becomes unit testing, and failure-driven data repair becomes debugging. Under this correspondence, model failures decompose into concept-level gaps and reasoning-chain breaks that can be traced back to specific deficiencies in the data and repaired through targeted patches, with each repair cycle producing consistent improvements across model scales and architectures without degrading general capabilities. We formalize this principle as Programming with Data and instantiate it across sixteen disciplines spanning the natural sciences, engineering, biomedicine, and the social sciences, releasing a structured knowledge base, benchmark suite, and training corpus as open resources. By demonstrating that the relationship between training data and model behaviour is structurally traceable and systematically repairable, this work establishes a principled foundation for the reliable engineering of human expertise into language models.

Fine-tuning large language models for vertical domains remains a labor-intensive and expensive process, requiring domain experts to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning, no prior work has tackled end-to-end LLM fine-tuning with agents. Can LLM-based agents automate this complete process? We frame this as a substantially open problem: agents must navigate an open-ended search space spanning data curation from diverse data sources, processing with complex tools, building a training pipeline, and iteratively refining their approach based on evaluation outcomes in rapidly growing logs--an overall scenario far more intricate than existing benchmarks. To study this question, we introduce FT-Dojo, an interactive environment comprising 13 tasks across 5 domains. We further develop FT-Agent, an autonomous system that mirrors human experts by leveraging evaluation-driven feedback to iteratively diagnose failures and refine fine-tuning strategies. Experiments on FT-Dojo demonstrate that purpose-built fine-tuning agents significantly outperform general-purpose alternatives, with FT-Agent achieving the best performance on 10 out of 13 tasks across all five domains. Ablations show that the approach generalizes effectively to 3B models, with additional insights on data scaling trade-offs and backbone sensitivity. Case analyses reveal that agents can recover from failures through cumulative learning from historical experience, while also exposing fundamental limitations in causal reasoning--highlighting both the promise and current boundaries of autonomous LLM fine-tuning.

LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environments over long horizons. However, existing benchmarks rarely evaluate planning under retrieval-limited tool visibility. To address this gap, we introduce PlanBench-XL, an interactive benchmark of 327 retail tasks over 1,665 tools that tests whether agents can iteratively retrieve usable tools, invoke them to uncover intermediate evidence for subsequent calls toward the final goal. PlanBench-XL further features an optional blocking mechanism that simulates real-world unpredictability through missing, failing, or distracting tool functions, forcing agents to detect disrupted paths and adapt at runtime. Experiments on ten leading LLMs show that massive-tool planning remains challenging: while GPT-5.4 achieves 51.90% accuracy in block-free settings, it collapses to 11.36% under the most severe blocking condition. Further analysis shows that agents are especially vulnerable when failures lack explicit error signals or when recovery requires longer alternative tool-use paths. These results establish PlanBench-XL as a testbed for diagnosing agentic planning failures and highlight the need for robust adaptive planning in long-horizon tasks with large, imperfect tool environments.

Understanding how Large Language Models (LLMs) perform complex reasoning and their failure mechanisms is a challenge in interpretability research. To provide a measurable geometric analysis perspective, we define the concept of the Reasoning Manifold, a latent low-dimensional geometric structure formed by the internal representations corresponding to all correctly reasoned generations. This structure can be conceptualized as the embodiment of the effective thinking paths that the model has learned to successfully solve a given task. Based on this concept, we build REMA, a framework that explains the origins of failures by quantitatively comparing the spatial relationships of internal model representations corresponding to both erroneous and correct reasoning samples. Specifically, REMA first quantifies the geometric deviation of each erroneous representation by calculating its k-nearest neighbors distance to the approximated manifold formed by correct representations, thereby providing a unified failure signal. It then localizes the divergence points where these deviations first become significant by tracking this deviation metric across the model's layers and comparing it against a baseline of internal fluctuations from correct representations, thus identifying where the reasoning chain begins to go off-track. Our extensive experiments on diverse language and multimodal models and tasks demonstrate the low-dimensional nature of the reasoning manifold and the high separability between erroneous and correct reasoning representations. The results also validate the effectiveness of the REMA framework in analyzing the origins of reasoning failures. This research connects abstract reasoning failures to measurable geometric deviations in representations, providing new avenues for in-depth understanding and diagnosis of the internal computational processes of black-box models.

Error analysis in NLP models is essential to successful model development and deployment. One common approach for diagnosing errors is to identify subpopulations in the dataset where the model produces the most errors. However, existing approaches typically define subpopulations based on pre-defined features, which requires users to form hypotheses of errors in advance. To complement these approaches, we propose iSEA, an Interactive Pipeline for Semantic Error Analysis in NLP Models, which automatically discovers semantically-grounded subpopulations with high error rates in the context of a human-in-the-loop interactive system. iSEA enables model developers to learn more about their model errors through discovered subpopulations, validate the sources of errors through interactive analysis on the discovered subpopulations, and test hypotheses about model errors by defining custom subpopulations. The tool supports semantic descriptions of error-prone subpopulations at the token and concept level, as well as pre-defined higher-level features. Through use cases and expert interviews, we demonstrate how iSEA can assist error understanding and analysis.

Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue resolution scenarios, these agents frequently fail due to the cascading effects of incorrect decision-making. These challenges are particularly pronounced for open-source LLMs with smaller parameter sizes, limited context windows, and constrained inference budgets, which contribute to increased error accumulation in agentic settings. To tackle these challenges, we present the Failure-Aware Meta-Agentic (FAMA) framework. FAMA operates in two stages: first, it analyzes failure trajectories from baseline agents to identify the most prevalent errors; second, it employs an orchestration mechanism that activates a minimal subset of specialized agents tailored to address these failures by injecting a targeted context for the tool-use agent before the decision-making step. Experiments across open-source LLMs demonstrate performance gains up to 27% across evaluation modes over standard baselines. These results highlight that targeted curation of context through specialized agents to address common failures is a valuable design principle for building reliable, multi-turn tool-use LLM agents that simulate real-world conversational scenarios.

Does continued scaling of large language models (LLMs) yield diminishing returns? Real-world value often stems from the length of task an agent can complete. We start this work by observing the simple but counterintuitive fact that marginal gains in single-step accuracy can compound into exponential improvements in the length of a task a model can successfully complete. Then, we argue that failures of LLMs when simple tasks are made longer arise from mistakes in execution, rather than an inability to reason. We propose isolating execution capability, by explicitly providing the knowledge and plan needed to solve a long-horizon task. We find that larger models can correctly execute significantly more turns even when small models have 100\% single-turn accuracy. We observe that the per-step accuracy of models degrades as the number of steps increases. This is not just due to long-context limitations -- curiously, we observe a self-conditioning effect -- models become more likely to make mistakes when the context contains their errors from prior turns. Self-conditioning does not reduce by just scaling the model size. In contrast, recent thinking models do not self-condition, and can also execute much longer tasks in a single turn. We conclude by benchmarking frontier thinking models on the length of task they can execute in a single turn. Overall, by focusing on the ability to execute, we hope to reconcile debates on how LLMs can solve complex reasoning problems yet fail at simple tasks when made longer, and highlight the massive benefits of scaling model size and sequential test-time compute for long-horizon tasks.

With Large Language Models (LLMs) being widely used across various tasks, detecting errors in their responses is increasingly crucial. However, little research has been conducted on error detection of LLM responses. Collecting error annotations on LLM responses is challenging due to the subjective nature of many NLP tasks, and thus previous research focuses on tasks of little practical value (e.g., word sorting) or limited error types (e.g., faithfulness in summarization). This work introduces ReaLMistake, the first error detection benchmark consisting of objective, realistic, and diverse errors made by LLMs. ReaLMistake contains three challenging and meaningful tasks that introduce objectively assessable errors in four categories (reasoning correctness, instruction-following, context-faithfulness, and parameterized knowledge), eliciting naturally observed and diverse errors in responses of GPT-4 and Llama 2 70B annotated by experts. We use ReaLMistake to evaluate error detectors based on 12 LLMs. Our findings show: 1) Top LLMs like GPT-4 and Claude 3 detect errors made by LLMs at very low recall, and all LLM-based error detectors perform much worse than humans. 2) Explanations by LLM-based error detectors lack reliability. 3) LLMs-based error detection is sensitive to small changes in prompts but remains challenging to improve. 4) Popular approaches to improving LLMs, including self-consistency and majority vote, do not improve the error detection performance. Our benchmark and code are provided at https://github.com/psunlpgroup/ReaLMistake.

High-quality, error-free datasets are a key ingredient in building reliable, accurate, and unbiased machine learning (ML) models. However, real world datasets often suffer from errors due to sensor malfunctions, data entry mistakes, or improper data integration across multiple sources that can severely degrade model performance. Detecting and correcting these issues typically require tailor-made solutions and demand extensive domain expertise. Consequently, automation is challenging, rendering the process labor-intensive and tedious. In this study, we investigate whether Large Language Models (LLMs) can help alleviate the burden of manual data cleaning. We set up an experiment in which an LLM, paired with Python, is tasked with cleaning the training dataset to improve the performance of a learning algorithm without having the ability to modify the training pipeline or perform any feature engineering. We run this experiment on multiple Kaggle datasets that have been intentionally corrupted with errors. Our results show that LLMs can identify and correct erroneous entries, such as illogical values or outlier, by leveraging contextual information from other features within the same row, as well as feedback from previous iterations. However, they struggle to detect more complex errors that require understanding data distribution across multiple rows, such as trends and biases.

Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning steps, leaving an open question: can a reasoning system effectively detect and recover from its own failures? We present ReFlect, a harness system for LLM reasoning that creates standalone error detection and recovery logic as a deterministic wrapper around the model. Controlled experiments across 6 reasoning domains show that prompt-level self-critique produces formulaic templates that flag no issues in 90 of 100 audited reflection blocks, and the investigated LLMs wrongly accept a wrong answer in at least 76\% of cases. Our ReFlect harness achieves task success rates ranging from 41\% on gpt-4o-mini to 56\% on Claude Sonnet 4.5 across six models spanning small and frontier scale, with per-model gains over Direct CoT ranging from +7 pp on Qwen2.5-72B to +29 pp on Claude Sonnet 4.5, and additionally raises SWE-bench patch-structural quality from 0\% (Direct CoT) to between 82\% (Qwen2.5-72B) and 87\% (GPT-4o). Notably, the harness gain is inversely proportional to the model's Direct CoT task success rate (the fitted slope is -1.69 with r=-0.76): each pp lost in baseline success rate is mechanically recovered by 1.69 pp of harness gain. We spot that adding structured reasoning state and operators yields only 15.0--18.7\% pair-mean on Llama-3.3-70B and Qwen2.5-72B because models at this scale cannot reliably populate the state its operators require. ReFlect is model-agnostic, training-free, and operates entirely at inference time.

Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need for developing LLMs that can effectively engage in logically consistent multi-turn dialogue, seek information and reason with incomplete data. To this end, we introduce a novel benchmark comprising a suite of multi-turn tasks each designed to test specific reasoning, interactive dialogue, and information-seeking abilities. These tasks have deterministic scoring mechanisms, thus eliminating the need for human intervention. Evaluating frontier models on our benchmark reveals significant headroom. Our analysis shows that most errors emerge from poor instruction following, reasoning failures, and poor planning. This benchmark provides valuable insights into the strengths and weaknesses of current LLMs in handling complex, interactive scenarios and offers a robust platform for future research aimed at improving these critical capabilities.

Robotic manipulation in open-world settings requires not only task execution but also the ability to detect and learn from failures. While recent advances in vision-language models (VLMs) and large language models (LLMs) have improved robots' spatial reasoning and problem-solving abilities, they still struggle with failure recognition, limiting their real-world applicability. We introduce AHA, an open-source VLM designed to detect and reason about failures in robotic manipulation using natural language. By framing failure detection as a free-form reasoning task, AHA identifies failures and provides detailed, adaptable explanations across different robots, tasks, and environments. We fine-tuned AHA using FailGen, a scalable framework that generates the first large-scale dataset of robotic failure trajectories, the AHA dataset. FailGen achieves this by procedurally perturbing successful demonstrations from simulation. Despite being trained solely on the AHA dataset, AHA generalizes effectively to real-world failure datasets, robotic systems, and unseen tasks. It surpasses the second-best model (GPT-4o in-context learning) by 10.3% and exceeds the average performance of six compared models including five state-of-the-art VLMs by 35.3% across multiple metrics and datasets. We integrate AHA into three manipulation frameworks that utilize LLMs/VLMs for reinforcement learning, task and motion planning, and zero-shot trajectory generation. AHA's failure feedback enhances these policies' performances by refining dense reward functions, optimizing task planning, and improving sub-task verification, boosting task success rates by an average of 21.4% across all three tasks compared to GPT-4 models.

Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still suffer from a multilingual reasoning gap, performing better in high-resource languages than in low-resource ones. While recent efforts have reduced this gap, its underlying causes remain largely unexplored. In this paper, we address this by showing that the multilingual reasoning gap largely stems from failures in language understanding-the model's inability to represent the multilingual input meaning into the dominant language (i.e., English) within its reasoning trace. This motivates us to examine whether understanding failures can be detected, as this ability could help mitigate the multilingual reasoning gap. To this end, we evaluate a range of detection methods and find that understanding failures can indeed be identified, with supervised approaches performing best. Building on this, we propose Selective Translation, a simple yet effective strategy that translates the multilingual input into English only when an understanding failure is detected. Experimental results show that Selective Translation bridges the multilingual reasoning gap, achieving near full-translation performance while using translation for only about 20% of inputs. Together, our work demonstrates that understanding failures are the primary cause of the multilingual reasoning gap and can be detected and selectively mitigated, providing key insight into its origin and a promising path toward more equitable multilingual reasoning. Our code and data are publicly available at https://github.com/deokhk/RLM_analysis.

Modern web dashboards and enterprise applications increasingly rely on complex, distributed microservices architectures. While these architectures offer scalability, they introduce significant challenges in debugging and observability. When failures occur, they often manifest as opaque error messages to the end-user such as Something went wrong. This masks the underlying root cause which may reside in browser side exceptions, API contract violations, or server side logic failures. Existing monitoring tools capture these events in isolation but fail to correlate them effectively or provide intelligible explanations to non technical users. This paper proposes a novel system for Automated Multi Source Debugging and Natural Language Error Explanation. The proposed framework automatically collects and correlates error data from disparate sources such as browser, API, server logs and validates API contracts in real time, and utilizes Large Language Models to generate natural language explanations. This approach significantly reduces Mean Time to Resolution for support engineers and improves the user experience by transforming cryptic error codes into actionable insights.

Automated decision systems produce operational data across multiple infrastructure layers, yet no single logging format captures the complete governance-relevant record of how a decision was reached. Regulatory frameworks prescribe what must be recorded without specifying a data model for how to record it -- a gap this paper terms the Fragmented Trace Problem. Following a design science methodology, the paper presents the Decision Event Schema (DES), a JSON Schema specification that bridges four infrastructure layers -- ML inference, rule/policy evaluation, cross-system coupling, and governance metadata -- within a single per-decision event structure. The schema employs degradation-aware field design: each of six top-level field groups maps to a governance evidence property and the degradation type it must resist. DES defines ten required root-level fields and introduces a tiered evidence strategy (lightweight, sampled, full) that enables organizations to match evidence completeness to decision risk and throughput. A mechanism feasibility analysis demonstrates compatibility with the highest-throughput integrity mechanisms at production-scale decision rates. Evaluation against 25+ existing formats confirms that DES is the only specification covering all four layers simultaneously. The schema offers practitioners a reference adoptable directly or adaptable through namespace extensions, and regulators a mapping from requirements to minimum evidence tiers.

LLMs for clinical decision support often fail under small but clinically meaningful input shifts such as masking a symptom or negating a finding, despite high performance on static benchmarks. These reasoning failures frequently go undetected by standard NLP metrics, which are insensitive to latent representation shifts that drive diagnosis instability. We propose a geometry-aware evaluation framework, LAPD (Latent Agentic Perturbation Diagnostics), which systematically probes the latent robustness of clinical LLMs under structured adversarial edits. Within this framework, we introduce Latent Diagnosis Flip Rate (LDFR), a model-agnostic diagnostic signal that captures representational instability when embeddings cross decision boundaries in PCA-reduced latent space. Clinical notes are generated using a structured prompting pipeline grounded in diagnostic reasoning, then perturbed along four axes: masking, negation, synonym replacement, and numeric variation to simulate common ambiguities and omissions. We compute LDFR across both foundation and clinical LLMs, finding that latent fragility emerges even under minimal surface-level changes. Finally, we validate our findings on 90 real clinical notes from the DiReCT benchmark (MIMIC-IV), confirming the generalizability of LDFR beyond synthetic settings. Our results reveal a persistent gap between surface robustness and semantic stability, underscoring the importance of geometry-aware auditing in safety-critical clinical AI.

Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate this skill in fragmented settings, failing to ensure context consistency or cover the full causal hierarchy. To address this, we pioneer METER to systematically benchmark LLMs across all three levels of the causal ladder under a unified context setting. Our extensive evaluation of various LLMs reveals a significant decline in proficiency as tasks ascend the causal hierarchy. To diagnose this degradation, we conduct a deep mechanistic analysis via both error pattern identification and internal information flow tracing. Our analysis reveals two primary failure modes: (1) LLMs are susceptible to distraction by causally irrelevant but factually correct information at lower level of causality; and (2) as tasks ascend the causal hierarchy, faithfulness to the provided context degrades, leading to a reduced performance. We belive our work advances our understanding of the mechanisms behind LLM contextual causal reasoning and establishes a critical foundation for future research. Our code and dataset are available at https://github.com/SCUNLP/METER .

Large language models (LLMs) have demonstrated remarkable reasoning capability in solving mathematical problems. However, existing approaches primarily focus on improving the quality of correct training data, e.g., distilling high-quality correct solutions from advanced models, neglecting the value contained in error data, potentially hindering the model's reflective ability. Though some studies attempt to leverage error data, they often involve complex mechanisms, such as Monte Carlo Tree Search (MCTS) to explore error nodes. In this work, we propose to enhance LLMs' reasoning ability by Learning from Errors for Mathematical Advancement (LEMMA). LEMMA constructs data consisting of an incorrect solution with an erroneous step and a reflection connection to a correct solution for fine-tuning. Specifically, we systematically analyze the model-generated error types and introduce an error-type grounded mistake augmentation method to collect diverse and representative errors. Correct solutions are either from fixing the errors or generating a fresh start. Through a model-aware smooth reflection connection, the erroneous solution is transferred to the correct one. By fine-tuning on the constructed dataset, the model is able to self-correct errors autonomously within the generation process without relying on external critique models. Experimental results demonstrate that LEMMA achieves significant performance improvements over other strong baselines.

LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sample. A natural approach would be to provide ground-truth labels to guide LLMs' reasoning. Contrary to intuition, we show that this yields no improvement in reasoning ability. We then propose CRAFT, a unified framework that mitigates both types of Step flaws, which builds a Reasoning Knowledge Graph (RKG) based on the consensus parts of multiple candidate traces, and synthesizes a high-quality trace through topological generation. Our approach improves label-prediction accuracy by 10+% on average, and consistently outperforms all baselines across both logical and mathematical reasoning benchmarks. Further, detailed benchmark evaluation proves that our method also improves the quality of LLMs' reasoning traces in multiple dimensions.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs' reasoning abilities. While most research primarily focuses on improving accuracy, it often neglects understanding and addressing the underlying patterns of errors. Current error classification methods rely on static and predefined categories, which limit their ability to capture the full spectrum of error patterns in mathematical reasoning. To enable systematic error analysis, we collect error samples from 15 different LLMs of varying sizes across four distinct MWP datasets using multiple sampling strategies. Based on this extensive collection, we introduce MWPES-300K, a comprehensive dataset containing 304,865 error samples that cover diverse error patterns and reasoning paths. To reduce human bias and enable fine-grained analysis of error patterns, we propose a novel framework for automated dynamic error classification in mathematical reasoning. Experimental results demonstrate that dataset characteristics significantly shape error patterns, which evolve from basic to complex manifestations as model capabilities increase. With deeper insights into error patterns, we propose error-aware prompting that incorporates common error patterns as explicit guidance, leading to significant improvements in mathematical reasoning performance.

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluations fall short in two ways: (1) reliance on coarse, subjective human-preference agreement; (2) focus on instruction-following or verifiable tasks, leaving open-ended agent executions unexplored. To address these gaps, we introduce REFLECT (REliable Fine-grained LLM judge Evaluation via Controlled inTervention), a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments. REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions on quality-screened agent execution traces. This yields verifiable, comprehensive, and fine-grained instances for validating the judge models. Our experiments show that current LLM judges remain unreliable: even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures, with especially poor performance on evidence verification. Together, our taxonomy and findings expose systematic judge limitations, reveal tradeoffs in cost and reliability, and offer actionable guidance for building more reliable evaluation pipelines for deep research agents.

Today's classical planners are powerful, but modeling input tasks in formats such as PDDL is tedious and error-prone. In contrast, planning with Large Language Models (LLMs) allows for almost any input text, but offers no guarantees on plan quality or even soundness. In an attempt to merge the best of these two approaches, some work has begun to use LLMs to automate parts of the PDDL creation process. However, these methods still require various degrees of expert input. We present NL2Plan, the first domain-agnostic offline LLM-driven planning system. NL2Plan uses an LLM to incrementally extract the necessary information from a short text prompt before creating a complete PDDL description of both the domain and the problem, which is finally solved by a classical planner. We evaluate NL2Plan on four planning domains and find that it solves 10 out of 15 tasks - a clear improvement over a plain chain-of-thought reasoning LLM approach, which only solves 2 tasks. Moreover, in two out of the five failure cases, instead of returning an invalid plan, NL2Plan reports that it failed to solve the task. In addition to using NL2Plan in end-to-end mode, users can inspect and correct all of its intermediate results, such as the PDDL representation, increasing explainability and making it an assistive tool for PDDL creation.

AI scientist systems, capable of autonomously executing the full research workflow from hypothesis generation and experimentation to paper writing, hold significant potential for accelerating scientific discovery. However, the internal workflow of these systems have not been closely examined. This lack of scrutiny poses a risk of introducing flaws that could undermine the integrity, reliability, and trustworthiness of their research outputs. In this paper, we identify four potential failure modes in contemporary AI scientist systems: inappropriate benchmark selection, data leakage, metric misuse, and post-hoc selection bias. To examine these risks, we design controlled experiments that isolate each failure mode while addressing challenges unique to evaluating AI scientist systems. Our assessment of two prominent open-source AI scientist systems reveals the presence of several failures, across a spectrum of severity, which can be easily overlooked in practice. Finally, we demonstrate that access to trace logs and code from the full automated workflow enables far more effective detection of such failures than examining the final paper alone. We thus recommend journals and conferences evaluating AI-generated research to mandate submission of these artifacts alongside the paper to ensure transparency, accountability, and reproducibility.