AgentCPM-Explore

Mar 20, 2026 · 1 min read
projects

🏆 My role: Project Lead

Stars

I led the development of AgentCPM-Explore, a 4B open-source agent focused on long-horizon deep exploration. I also helped build the surrounding stack, including the tool sandbox, training pipeline, and evaluation workflow.

Key highlights:

  • ✅ First 4B open-source agent model to appear on eight classic long-horizon benchmarks
  • ✅ Supports 100+ turns of continuous interaction with dynamic strategy adjustment
  • ✅ End-to-end open source across model, training, inference, and tool sandbox infrastructure
Autonomous Agents Reinforcement Learning
Haotian Chen
Authors
Haotian Chen (he/him)
Research Assistant Professor · LLM Post-Training / AI4AI
I am a Research Assistant Professor at the School of Artificial Intelligence, Shanghai Jiao Tong University, where I work with Prof. Junchi Yan at RethinkLab. I study how to build AI systems that can automate long-horizon, effort-intensive, and creativity-demanding tasks such as research, engineering, and development. My current work focuses on LLM post-training for autonomous agents, agent memory and continual learning, and AI4Research / AI4AI. Before joining SJTU, I received my PhD in Data Science from Fudan University, advised by Prof. Xiangdong Zhou, and completed postdoctoral research at Tsinghua University (THUNLP), working with Prof. Zhiyuan Liu and Prof. Maosong Sun. I was also a research intern at the Machine Learning Research Group of Microsoft Research Asia, mentored by Xiao Yang, and at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, working with Prof. Yang Yu.