Zihan Xu

CUARewardBench: Benchmark for Evaluating Reward Models on Computer-using Agent Trajectories

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Training-Free Group Relative Policy Optimization

RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models

FlowAgent: a New Paradigm for Workflow Agent