AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
2月 1, 2026·
,,,,,,,,,,,,,,,,,,·
0 分钟阅读时长
Haotian Chen
Xin Cong
Shengda Fan
Yuyang Fu
Ziqin Gong
Yaxi Lu
Yishan Li
Boye Niu
Chengjun Pan
Zijun Song
Huadong Wang
Yesai Wu
Yueying Wu
Zihao Xie
Yukun Yan
Zhong Zhang
Yankai Lin
Zhiyuan Liu
Maosong Sun
摘要
We develop a unified tool sandbox environment management framework with end-to-end agent RL training. The 4B-parameter agent achieves SOTA among same-scale models, surpassing GPT-5 and Claude-4.5-Sonnet on GAIA and HLE benchmarks.
类型
出版物
ArXiv Preprint 2026
Authors
Haotian Chen
(he/him)
Research Assistant Professor
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 autonomous agents, large language models, and AI4Research. 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.