About Me
I am a master's student in Artificial Intelligence at Zhejiang University, expected to graduate in June 2027. I am a member of the Interactive Data Group (IDG) at the State Key Laboratory of CAD&CG, where I am jointly advised by Prof. Yingcai Wu and Prof. Di Weng.
My research lies at the intersection of natural language processing, human-computer interaction, and data intelligence. I build learning agents that improve through interaction, use tools over long horizons, and remain grounded in the data and context surrounding their decisions.
Recently, I have focused on agentic reinforcement learning, self-improving systems, and human–AI collaboration, with particular interest in fine-grained credit assignment, long-term coherence, and interactive systems that make model behavior easier to inspect and refine.
News
Released MerchantBench for evaluating long-term coherence in e-commerce agents.
Released SPADER with code and model weights for long-horizon Multi-Answer QA.
Joined Alibaba's 1688 team to work on self-improving agents and long-horizon RL.
Cerebra appeared at CHI 2026 in Barcelona.
Completed a research internship at Microsoft on the Wide Search Agent.
Selected Publications
* Equal contribution; † Corresponding author
