Zhi Wang

ExGRPO: Learning to Reason from Experience

Diversity-Incentivized Exploration for Versatile Reasoning

Scalable In-Context Q-Learning

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Learning to Reason under Off-Policy Guidance

Mixture-of-Experts Meets In-Context Reinforcement Learning

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision