AgentCPM-Explore
2月 1, 2026
·
1 分钟阅读时长
🏆 Role: Project Lead
Developed a unified tool sandbox environment management framework with end-to-end agent reinforcement learning. The agent leverages past experience memory for task decision-making and adapts strategies based on dynamic environment feedback.
Key Results:
- ✅ SOTA among same-scale (4B) models on GAIA & HLE benchmarks
- ✅ Surpasses GPT-5 and Claude-4.5-Sonnet (closed-source models)
- ✅ End-to-end agent RL with unified sandbox environment
Authors
Haotian Chen
(he/him)
Assistant Researcher
Haotian Chen is an Assistant Researcher at the School of Artificial Intelligence, Shanghai Jiao Tong University, working with Prof. Junchi Yan at RethinkLab. His research goal is to understand and develop AI for automating tasks that require extensive time, effort, and creative thinking. He works on automating data-driven scientific research, contributing to both alleviating the burden on humans and revolutionizing human productivity. His research focuses on Autonomous Agents, Large Language Models, and AI4Research. He received his PhD in Data Science from Fudan University and completed postdoctoral research at Tsinghua University (THUNLP), where he worked with Prof. Zhiyuan Liu and Prof. Maosong Sun. He was also a research intern at Microsoft Research Asia, where the RD-Agent project he co-developed was featured in the Microsoft Build 2025 Global Keynote.