Wenqi Shi

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

CellForge: Agentic Design of Virtual Cell Models

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration