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.
Professional Summary
I am an Assistant Researcher 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 and completed postdoctoral research at Tsinghua University (THUNLP). I was also a research intern at Microsoft Research Asia, where I co-developed RD-Agent, a project later featured in the Microsoft Build 2025 global keynote.
Education
PhD in Data Science
2018-09-01
2024-06-30
Fudan University
BEng in Electrical Engineering
2014-09-01
2018-06-30
Dalian University of Technology
Interests
Autonomous Agents
Large Language Models
AI4Research
Agent Reinforcement Learning
Tool Learning
Experience
Assistant Researcher
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 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 Electrical Engineering
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.
🔬 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:
🧪 AI4Research — I build AI research assistants for literature retrieval, experiment design, data analysis, and hypothesis generation and verification.
🤖 Autonomous Agents — I develop agent models and systems with environment perception, memory, planning, and tool-use capabilities, with LLMs as the core intelligence.
🧠 Foundation Models — I explore how to train and adapt general-purpose models for language understanding, knowledge representation, multimodal fusion, and downstream generalization.
📄 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.
📚 All Publications
(2026).
Learning from Human Demonstrations Enables Adaptive GUI Agents.
ARR (pre-submission).
(2026).
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents.
ArXiv 2026.
(2026).
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents.
KDD 2026 (submitted).
(2026).
Test-Time Exploration in Unknown Environments.
KDD 2026 (submitted).
(2026).
AtomMem: Learnable Dynamic Agentic Memory with Atomic Memory Operation.
ACL 2026 (submitted).
💻 Open-Source Projects
All my open-source contributions revolve around the central theme of LLM-powered agents, forming a cohesive ecosystem: Data (AgentCPM-GUI, ToolLLM) → Algorithm (AgentRL, AgentCPM-Explore, MiniCPM4-MCP) → Execution (RD-Agent, XAgent) → Evaluation (ToLeaP) → Application (QingXiaoDa).
RD-Agent
🔬 **Core Founding Member & Primary Coder** · I helped build an automated R&D agent for data science and finance …
•
1 min read
AgentCPM-Explore
🏆 **Project Lead** · I led an open-source 4B agent model for long-horizon deep exploration …
•
1 min read
AgentRL
🏆 **Project Lead** · Fully asynchronous agent RL training infrastructure for the AgentCPM model family `100+ Tools` · `20+ Benchmarks` · `Full-cycle Visualization`
•
1 min read
MiniCPM4-MCP
🏆 **Project Lead** · Edge-scale (8B) agent LLM mastering MCP tools [](https://github.com/OpenBMB/MiniCPM) …
•
1 min read
🎓 Academic Service
🧑🏫 Student Supervision — I co-supervise undergraduate, master’s, and PhD students on LLM agents and data mining.
📝 Conference Reviewing — I regularly review for venues including NeurIPS, ICLR, EMNLP, KDD, WWW, and COLING.
📰 Journal Reviewing — I have also reviewed for journals such as TKDE, Science China, and AI Open.
🎤 Invited Talks — Recent invited talks include Autonomous Agents and Tool Learning with LLMs (RLChina 2025) and LLM-Driven Autonomous Agents (Huawei OpenHarmony AI Agent TSG).
💰 Research Grants — I currently serve as PI for the China Postdoctoral Science Foundation General Grant and the National Postdoctoral Researcher Program Category C.
📬 Contact
Feel free to reach out if you would like to discuss research ideas, collaborations, or open-source projects.
✉️ Email: htchen@tsinghua.edu.cn
🐙 GitHub: github.com/Hytn
✖️ X: @HytnChen
🎓 Google Scholar: scholar profile