AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
ArXiv 2026. First author. Open-source 4B agent model achieving SOTA on GAIA & HLE, surpassing GPT-5 and Claude-4.5-Sonnet.
Biography
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.
Education
PhD in Data Science
2018-09-01
2024-06-30
Fudan University
BEng in EE
2014-09-01
2018-06-30
Dalian University of Technology
Interests
Autonomous Agents
Large Language Models
AI4Research
Agent Reinforcement Learning
Tool Learning
Experience
Research Assistant Professor
Shanghai Jiao Tong University
School of Artificial Intelligence, RethinkLab. I work with Prof. Junchi Yan on autonomous agents, LLMs, and AI4Research.
Postdoctoral Researcher
Tsinghua University
Department of Computer Science and Technology, THUNLP. I worked with Prof. Zhiyuan Liu and Prof. Maosong Sun on autonomous agents, LLMs, and tool-use reinforcement learning for agents. Honor: Tsinghua “Shuimu Scholar” Program.
Research Intern
Microsoft Research Asia
Machine Learning Research Group. I worked with Xiao Yang and Jiang Bian on autonomous agents and LLMs, and served as a core contributor to RD-Agent. Honor: Microsoft “Star of Tomorrow”.
Research Intern
Tsinghua University (IIIS)
Institute for Interdisciplinary Information Sciences. I worked with Prof. Yang Yu on LLM safety auditing and AI decision-bias analysis.
Education
PhD in Data Science
Fudan University
School of Computer Science and Technology. Advisor: Prof. Xiangdong Zhou. I worked on NLP, data mining, and information extraction, and received honors including Outstanding Student, Outstanding Graduate, and Academic Excellence Scholarship.
BEng in EE
Dalian University of Technology
School of Electrical Engineering. Advisors: Prof. Qianjin Yue and Prof. Mingfeng He. I ranked 1/74 in the program and graduated as a Provincial Outstanding Graduate.
๐ฌ Research
I study how to build AI systems that can automate long-horizon work in research, engineering, and development. A central goal of my work is to make data-driven scientific research more scalable, reliable, and productive. I currently focus on three closely connected directions:
๐งช AI4Research โ I build AI research assistants for literature retrieval, experiment design, data analysis, and hypothesis generation and verification.
๐ค Autonomous Agents โ I develop agent models and systems with environment perception, memory, planning, and tool-use capabilities, with LLMs as the core intelligence.
๐ง Foundation Models โ I explore how to train and adapt general-purpose models for language understanding, knowledge representation, multimodal fusion, and downstream generalization.
๐ Featured Publications
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
EMNLP 2025 Demo. GUI agents with reinforcement fine-tuning. 1,200+ GitHub Stars.
zhong-zhang
MiniCPM4: Ultra-Efficient LLMs on End Devices
ArXiv 2025. Team contribution (led MCP agent capabilities). 8,300+ GitHub Stars.
minicpm-team
Towards Data-Centric Automatic Research and Development
ArXiv 2024. First author. RD-Agent for automatic R&D. Featured in Microsoft Build 2025 Keynote. 11,400+ GitHub Stars.
๐ All Publications
(2026).
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents.
ArXiv 2026.
(2026).
Reflective Reinforcement Tool Learning.
ACL 2026 (submitted).
(2026).
ToLeaP: Rethinking Development of Tool Learning with Large Language Models.
ACL 2026 (submitted).
(2025).
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning.
In EMNLP 2025 Demo.
(2025).
MiniCPM4: Ultra-Efficient LLMs on End Devices.
ArXiv 2025.
(2024).
Collaborative Evolving Strategy for Automatic Data-Centric Development.
ArXiv 2024.
(2024).
Towards Data-Centric Automatic Research and Development.
ArXiv 2024.
(2024).
OODREB: Benchmarking State-of-the-Art Methods for Out-Of-Distribution Generalization on Relation Extraction.
In WWW 2024.
(2024).
RD2Bench: Toward Data-Centric Automatic R&D.
ICLR 2024 Workshop.
(2024).
Rethinking the Development of Large Language Models from the Causal Perspective: A Legal Text Prediction Case Study.
In AAAI 2024.
(2023).
SALAS: Supervised Aspect Learning Improves Abstractive Multi-Document Summarization through Aspect Information Loss.
In ECML-PKDD 2023.
๐ป Open-Source Projects
All my open-source contributions revolve around the central theme of LLM-powered agents, forming a cohesive ecosystem: Data (AgentCPM-GUI) โ Algorithm (AgentRL, AgentCPM-Explore, MiniCPM4-MCP) โ Execution (RD-Agent) โ Evaluation (ToLeaP).
RD-Agent
๐ฌ **Core Founding Member & Primary Coder** ยท I helped build an automated R&D agent for data science and finance โฆ
โข
1 min read
AgentCPM-Explore
๐ **Project Lead** ยท I led an open-source 4B agent model for long-horizon deep exploration โฆ
โข
1 min read
AgentRL
๐ **Project Lead** ยท Fully asynchronous agent RL training infrastructure for the AgentCPM model family `100+ Tools` ยท `20+ Benchmarks` ยท `Full-cycle Visualization`
โข
1 min read
MiniCPM4-MCP
๐ **Project Lead** ยท Edge-scale (8B) agent LLM mastering MCP tools [](https://github.com/OpenBMB/MiniCPM) โฆ
โข
1 min read
AgentCPM-GUI
๐ฑ **Training Data Lead** ยท Multimodal LLM-based GUI agent for mobile & desktop โฆ
โข
1 min read
๐ Academic Service
๐งโ๐ซ Student Supervision โ I co-supervise undergraduate, master’s, and PhD students on LLM agents and data mining.
๐ Conference Reviewing โ I regularly review for venues including NeurIPS, ICLR, EMNLP, KDD, WWW, and COLING.
๐ฐ Journal Reviewing โ I have also reviewed for journals such as TKDE, Science China, and AI Open.
๐ค Invited Talks โ Recent invited talks include Autonomous Agents and Tool Learning with LLMs (RLChina 2025) and LLM-Driven Autonomous Agents (Huawei OpenHarmony AI Agent TSG).
๐ฐ Research Grants โ I currently serve as PI for the China Postdoctoral Science Foundation General Grant and the National Postdoctoral Researcher Program Category C.
๐ฌ Contact
Feel free to reach out if you would like to discuss research ideas, collaborations, or open-source projects.
โ๏ธ Email: haotian.chen@163.com / ht1ian.chen@gmail.com
๐ GitHub: github.com/Hytn
โ๏ธ X: @HytnChen
๐ Google Scholar: scholar profile