AgentBaton: Efficient Model Collaboration in Agentic Tasks Paper • 2610.35959 • Published 26 days ago • 25
Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents Paper • 2611.14320 • Published 10 days ago • 74
P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Paper • 2611.03953 • Published 17 days ago • 72
SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Paper • 2611.15777 • Published 9 days ago • 72
Experience-Handoff Reinforcement Learning for Recursive Self-Improvement Paper • 2611.16409 • Published 8 days ago • 10
Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis Paper • 2611.08219 • Published 15 days ago • 9
Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction Paper • 2611.10439 • Published 13 days ago • 12
Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents Paper • 2611.17167 • Published 8 days ago • 39
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation Paper • 2610.33024 • Published Oct 10 • 22
Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges Paper • 2610.35193 • Published 25 days ago • 24
Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution Paper • 2610.32285 • Published 28 days ago • 36
DynaFlow: Learning Free-Form Multi-Agent Orchestration Paper • 2610.34467 • Published 26 days ago • 41
Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents Paper • 2610.33956 • Published 26 days ago • 36
PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions Paper • 2610.40453 • Published 22 days ago • 14
MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation Paper • 2610.23234 • Published about 1 month ago • 12
DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation Paper • 2610.32002 • Published 29 days ago • 16
RSIHub: A Composable Framework for Agent-Evolution Methods Paper • 2610.32253 • Published 28 days ago • 45