Hi, welcome to my homepage! I am Zhaoxi Zhang, a second-year MPhil student at the School of Computer Science, Peking University, advised by Prof. Yunfang Wu. My research interests span NLP and large language models. I have worked on model merging, reinforcement learning, and multi-agent systems. My current research focuses on training LLMs for complex agentic tasks — including reinforcement learning, on-policy distillation, and SFT — as well as developing rigorous benchmarks to evaluate LLMs’ agentic capabilities.

I firmly believe that LLMs can be substantially enhanced through effective interaction with external environments. Toward this goal, I am working on building such environments and developing RL algorithms to strengthen this capability.

Education

• MPhil in Computer Science, Peking University, 2025–2028
• B.S. in Computer Science, Beijing Institute of Technology, 2021–2025

Internship

• Research Intern, Baidu Inc., January 2026 – present
• Research Intern, Zhongguancun Institute of Artificial Intelligence (ZIAI), March 2025 – December 2025
• Research Assistant, Center for Brain-Inspired Computing Research, Tsinghua University, November 2024 – February 2025

Selected Publication

• RepoZero: Can LLMs Generate a Code Repository from Scratch?

  Zhaoxi Zhang, Yiming Xu, Weikang Li, Jiahui Liang, Yunfang Wu.

  arXiv preprint arXiv:2605.07122

• One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

  Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang, Yiming Xu, Zhixiang Wang, Kun Liang, Weikang Li, Jiahui Liang, Deguo Xia, Jizhou Huang, Jiyan He, Shuxin Zheng, Yunfang Wu.

  ICML 2026

• No Free Lunch: Rethinking Internal Feedback for LLM Reasoning

  Yanzhi Zhang*, Zhaoxi Zhang*, Haoxiang Guan, Yilin Cheng, Yitong Duan, Chen Wang, Yue Wang, Shuxin Zheng, et al.

  arXiv preprint arXiv:2506.17219

• 3DM: Distill, Dynamic Drop, and Merge for Debiasing Multi-modal Large Language Models

  Zhaoxi Zhang, Sanwoo Lee, Zhixiang Wang, Yunfang Wu

  ACL 2025, pp. 14049–14059

• Transferring Knowledge from High-Quality to Low-Quality MRI for Adult Glioma Diagnosis

  Y Zhao, L Bai, Z Zhang, Y Wu, M Islam, H Ren

  MICCAI 2024