4 papers · 1 filter
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
Zhiyuan Zhai, Xin Wang
Group-relative RL training (GRPO) samples a small group of parallel rollouts for every training prompt and uses their within-group reward spread to compute per-trajectory advantage…
Revisable by Design: A Theory of Streaming LLM Agent Execution
Zhiyuan Zhai, Ming Li, Xin Wang
Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon complet…
Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
Zhiyuan Zhai, Wenjing Yan, Xiaodan Shao +1
Does reinforcement learning genuinely expand what LLM agents can do, or merely make them more reliable? For static reasoning, recent work answers the second: base and RL pass@k cur…
Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
Zhiyuan Zhai, Bingcong Li, Bingnan Xiao +2
Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improvi…