I am a senior undergraduate student studying Data Science at the University of Michigan and Mechanical Engineering at Shanghai Jiao Tong University. I will be joining UCLA as a Computer Science Ph.D. student, advised by Prof. Yangruibo (Robin) Ding.

I am a research intern at Princeton University, working with Prof. Mengdi Wang on AI agent systems and with Prof. Sanfeng Wu on AI for quantum materials, where I work closely with Jiahao Qiu and Shilong Liu. I also work with Prof. Yan Chen at Northwestern University on LLM reasoning and AI safety, where I work closely with Haozheng (Robin) Luo. At the University of Michigan, I work closely with Xinliang (Frederick) Zhang and Kaijian Zou.

My research interests lie in Large Language Models and Agentic AI, with a focus on LLM reasoning, self-evolving AI agents, and the safety & robustness of LLM-based systems. I also have experience in code generation and multimodal systems.

If you are interested in collaborating, feel free to reach out 🤝

🧠 LLM Reasoning 🤖 AI Agents 💻 Code Generation 🛡️ Safety & Robustness 🔄 Self-Evolving Systems

News

  • 2026.05: My two co-first authored papers, On Path to Multimodal Historical Reasoning: HistBench and HistAgent and Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations, are accepted to ICML 2026!
  • 2026.03: My first-authored paper Learning Agent Routing From Early Experience and co-first authored paper On Path to Multimodal Historical Reasoning: HistBench and HistAgent are accepted to the Lifelong Agent Workshop at ICLR 2026!
  • 2025.08: My first co-authored paper in AI area, EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety, is accepted to EMNLP 2025 Main Conference (oral)!

Education

  • 2024.08 - present, University of Michigan, B.S.E in Data Science.
  • 2022.09 - present, Shanghai Jiao Tong University, B.E in Mechanical Engineering.

Publications and Preprints

ICML 2026
sym

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations

Haozheng Luo*, Yimin Wang*, Jiahao Yu, Binghui Wang, Yan Chen

* These authors contributed equally to this work.

ICML 2026
sym

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

Jiahao Qiu*, Fulian Xiao*, Yimin Wang*, Yuchen Mao*, Yijia Chen*, Xinzhe Juan, Shu Zhang, Siran Wang, Xuan Qi, Tongcheng Zhang, Zixin Yao, Jiacheng Guo, Yifu Lu, Charles Argon, Jundi Cui, Daixin Chen, Junran Zhou, Shuyao Zhou, Zhanpeng Zhou, Ling Yang, Shilong Liu, Hongru Wang, Kaixuan Huang, Xun Jiang, …, Xi Gao, Mengdi Wang

* These authors contributed equally to this work

Accepted by Lifelong Agent @ ICLR 2026; ICML 2026

LLA @ ICLR 2026
sym

Learning Agent Routing From Early Experience

Yimin Wang*, Jiahao Qiu*, Xuan Qi, Xinzhe Juan, Jingzhe Shi, Zelin Zhao, Hongru WANG, Shilong Liu, Mengdi Wang

* These authors contributed equally to this work.

Accepted by Lifelong Agent @ ICLR 2026

EMNLP 2025 Oral
sym

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety

Jiahao Qiu*, Yinghui He*, Xinzhe Juan*, Yimin Wang, Yuhan Liu, Zixin Yao, Yue Wu, Xun Jiang, Ling Yang, Mengdi Wang

* These authors contributed equally to this work.

Preprint
sym

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes

Jiahao Qiu*, Xinzhe Juan*, Yimin Wang*, Ling Yang*, Xuan Qi, Tongcheng Zhang, Jiacheng Guo, Yifu Lu, Zixin Yao, Hongru Wang, Shilong Liu, Xun Jiang, Liu Leqi, Mengdi Wang

* These authors contributed equally to this work.

Preprint
sym

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

Jiahao Qiu*, Xuan Qi*, Tongcheng Zhang*, Xinzhe Juan, Jiacheng Guo, Yifu Lu, Yimin Wang, Zixin Yao, Qihan Ren, Xun Jiang, Xing Zhou, Dongrui Liu, Ling Yang, Yue Wu, Kaixuan Huang, Shilong Liu, Hongru Wang, Mengdi Wang

* These authors contributed equally to this work.

* These authors contributed equally to this work.


Selected Projects

sym

Come on, Lei!

Developed by Li Qichen, Wang Yimin, Wu Lv, You Yuchen

  • a responsive Elm-based interface with clear feedback, built real-time interactions via Elm message passing, and integrated original hand-drawn art into a cohesive UI.

Service

  • Reviewer: COLM 2026, ICLR 2026 Workshops.
  • 2025.09 - 2025.12, Grader for EECS496 Professionalism (Major Design Experience), University of Michigan, USA.
  • 2024.09 - 2024.12, Teaching assistant for ME395 Laboratory I, Shanghai Jiao Tong University, China.
  • 2024.05 - 2024.08, Teaching assistant for ENGR100 Intro to Engineering, Shanghai Jiao Tong Univeristy, China.