Ziming You

游孜明
ziming.you [AT] ntu.edu.sg Scholar GitHub Twitter CV

Large Language Models · Reinforcement Learning · Language Agents

Ziming You

Recently, my research has centered on self-evolving and agentic systems: enabling language agents to learn from experience, improve through reinforcement learning, and coordinate reliably across tasks and environments.

I am always open to new collaborations and discussions. If you would like to discuss potential collaborations, feel free to reach out.

Bio

I am a Research Associate at NTU College of Computing and Data Science and BREATHE AI Lab. I will start my Ph.D. in Spring 2027, advised by Prof. Wei Lu.

Recently, my research has focused on self-evolving and agentic systems, with an emphasis on how language agents can acquire experience, improve through reinforcement learning, and collaborate robustly across open-ended tasks.

News

  1. ✨ Started a new chapter as a Research Associate at NTU College of Computing and Data Science and BREATHE AI Lab.
  2. 🌱 I will start my Ph.D. at NTU CCDS in Spring 2027, advised by Prof. Wei Lu.
  3. 🧭 Joined Seed Edge, ByteDance, and started research on self-evolution, agentic RL, and test-time scaling.
  4. 🍂 Attended EMNLP 2025 in Suzhou.
  5. 🎓 Congratulations! I received my M.Eng. in Software Engineering from Peking University.
  6. 📝 DatawiseAgent was accepted to EMNLP 2025 Main Conference.
  7. 🇸🇬 Attended ICLR 2025 in Singapore for Internet of Agents. Feel free to contact me if you are around Singapore.
  8. 🌐 Internet of Agents was accepted to ICLR 2025 as a Spotlight paper.

Publications

Google Scholar

Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

Weize Chen*, Ziming You*, Ran Li*, Yitong Guan*, Chen Qian, Chenyang Zhao, Cheng Yang, Ruobing Xie, Zhiyuan Liu, Maosong Sun

ICLR 2025 (Spotlight, top 5.1%)

Paper Code

DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation

Ziming You, Yumiao Zhang, Dexuan Xu, Yiwei Lou, Yandong Yan, Wei Wang, Huamin Zhang, Yu Huang

EMNLP 2025 Main Conference

Paper Code

Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration

Yilong Li*, Chen Qian*, Yu Xia, Ruijie Shi, Yufan Dang, Zihao Xie, Ziming You, Weize Chen, Cheng Yang, Liu Weichuan, Ye Tian, Xuantang Xiong, Lei Han, Zhiyuan Liu, Maosong Sun

Paper

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones

Lifan Yuan*, Weize Chen*, Yuchen Zhang, Ganqu Cui, Hanbin Wang, Ziming You, Ning Ding, Zhiyuan Liu, Maosong Sun, Hao Peng

Paper Code

Experience

Research Associate

NTU College of Computing and Data Science / BREATHE AI Lab

Advisor: Prof. Wei Lu

Research Intern in Self Evolution

Seed Edge, ByteDance

Agentic RL and test-time scaling

Research Intern in Post-training

Tsinghua University

Advisor: Prof. Zhiyuan Liu; RL for LLM reasoning

Research Intern in Multi-agent Systems

Tsinghua University

Advisor: Prof. Zhiyuan Liu; Internet of Agents

LLM Algorithms Intern

ModelBest Inc. (面壁智能)

Service