Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published 4 days ago • 34
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks Paper • 2604.20987 • Published Apr 22 • 22
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks Paper • 2604.20987 • Published Apr 22 • 22
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills Paper • 2604.05333 • Published Apr 7 • 24
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models Paper • 2603.24935 • Published Mar 26 • 2