5 papers
Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control
Qi Zhao, Guozheng Ma, Yilun Kong +9
Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many…
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations
Lirong Che, Yuzhe yang, Peiwen lin +3
Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptati…
GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning
Jiaqi Wu, Qinlao Zhao, Zefeng Chen +4
Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAc…
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
Yilun Kong, Guozheng Ma, Qi Zhao +4
Despite recent advancements in offline multi-task reinforcement learning (MTRL) have harnessed the powerful capabilities of the Transformer architecture, most approaches focus on a…
Lifelong Safety Alignment for Language Models
Haoyu Wang, Zeyu Qin, Yifei Zhao +4
LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing…