Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
Paper β’ 2605.02801 β’ Published β’ 5
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation
xxzccΒ
submitted a
paper to Daily Papers 2 days ago
SiweiWuΒ
authored 2
papers 11 days ago
JinChengRenΒ
submitted a
paper to Daily Papers 15 days ago
JoeYingΒ
authored a
paper 17 days ago
JasperHaozheΒ
authored 13
papers 21 days ago
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
Paper β’ 2509.03646 β’ Published β’ 33
Reverse-Engineered Reasoning for Open-Ended Generation
Paper β’ 2509.06160 β’ Published β’ 151
VideoScore2: Think before You Score in Generative Video Evaluation
Paper β’ 2509.22799 β’ Published β’ 26
Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports
Paper β’ 2510.02190 β’ Published β’ 19
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Paper β’ 2510.15349 β’ Published
TR-DQ: Time-Rotation Diffusion Quantization
Paper β’ 2503.06564 β’ Published
From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
Paper β’ 2511.23031 β’ Published β’ 1
CogDoc: Towards Unified thinking in Documents
Paper β’ 2512.12658 β’ Published
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Paper β’ 2601.15876 β’ Published β’ 92
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining
Paper β’ 2603.11103 β’ Published β’ 9
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Paper β’ 2603.16124 β’ Published β’ 3
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper β’ 2603.27538 β’ Published β’ 145
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Paper β’ 2604.11626 β’ Published β’ 101
JasperHaozheΒ
submitted a
paper to Daily Papers 22 days ago
wanngΒ
updated a
dataset 23 days ago