ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement Paper • 2609.14857 • Published Sep 14 • 55
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report Paper • 2608.15763 • Published Aug 22 • 54
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Paper • 2608.25593 • Published Aug 26 • 63
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Paper • 2608.05987 • Published Aug 6 • 83
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance Paper • 2608.00782 • Published Aug 1 • 14
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks Paper • 2606.12344 • Published Jun 10 • 35
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents Paper • 2606.05806 • Published Jun 4 • 27
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents Paper • 2605.30723 • Published May 29 • 14
GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection Paper • 2605.28534 • Published May 27 • 24
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions Paper • 2605.27141 • Published May 26 • 18
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments Paper • 2605.27209 • Published May 26 • 13
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning Paper • 2605.28424 • Published May 27 • 27
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning Paper • 2605.28424 • Published May 27 • 27
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization Paper • 2604.02268 • Published Apr 2 • 99