Ying Wen

Learning to Reason in Structured In-context Environments with Reinforcement Learning

Progra: Progress-Aware Reinforcement Learning for Multi-Turn Function Calling

Towards Monotonic Improvement in In-Context Reinforcement Learning

STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

DSR: Reinforcement Learning with Dynamical Skill Refinement

Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games