I am currently a fourth-year PhD Student in the College of Computer Science and Technology at Zhejiang University, under the supervision of Prof. Fei Wu and Prof. Kun Kuang in the DCD (Digital media Computing & Design) Lab. During my PhD journey, I am also fortunate to collaborate with Prof. Li Shen from Sun Yat-sen University and Zhengyu Chen from Meituan remotely.

My research interests include:

• Agentic RL for complex interaction scenarios (e.g. Tool Use, DeepResearch, Code Agent);
• LLM Reasoning, especially for real-world open-domain unverifiable scenarios;
• Trustworthiness, including models’ generalization, safety, hallucination and so on.

★★★ Feel free to reach out to me for academic discussions and collaborations!

★★★ I am currently seeking job opportunities and will graduate in June 2027. If you have any suitable positions, please feel free to reach out.

📝 Publications

Please look through my Google Scholar for the publications.

💻 Internships

• 2025.08 - 2026.02: Meituan, LongCat Team

  Responsible for Agentic Tool Use: (1) Cold Start and RL Strategy; (2) Date Synthesis and Data Selection

  Core Contributor of LongCat-Flash-Thinking-2601 Technical Report

• 2024.06 - 2025.06: AntGroup, Ling Team

  Responsible for LLM Post-Training: (1) Multi-Objective Policy Optimization; (2) Data Mixture Optimization

📖 Educations

• 2022.09 - 2027.06 (Expected), PhD candidate, Zhejiang University
• 2018.09 - 2022.06, Undergraduate, Nanjing University of Aeronautics and Astronautics