👤 About Me
I am a researcher with research interests in Artificial Intelligence, Reasoning & Planning, and AI Agent. I obtained my Ph.D. degree from Department of Computer Science and Technology in Nanjing University in June 2022, where I was very fortunate to be advised by professor Yu-Feng Li (李宇峰). Currently, I am an Assistant Professor in School of Intelligence Science and Technology, Nanjing University (Suzhou Campus). I am also a member of LAMDA Group (机器学习与数据挖掘研究所), which is led by professor Zhi-Hua Zhou (周志华).
Outside of work, I also enjoy hiking, mountaineering, photography, and travel.
Research Areas: Agent, LLM Reasoning and Planning, World Model, Neuro-Symbolic Learning, Tabular ML⋯
招收硕士生、直博生,申请之前请阅读:研究生招生说明。
招收本科科研实习生,南大苏州校区同学优先,申请之前请阅读:本科生进组说明。
欢迎有兴趣的同学邮件联系(guolz@nju.edu.cn),附上你的简历,简要介绍你的研究兴趣和研究经历。
🔬 Research
The long-term research goal of our team is to build AI Agent in both digital and physical worlds, contributing to the advancement of artificial general intelligence (AGI). Our core approach centers on neuro-symbolic learning, which bridges data-driven machine learning with knowledge-driven symbolic reasoning, often regarded as the hallmark of third-generation AI. The neural component provides grounding in perception and physical interaction, while the symbolic component augments reasoning and planning.
Recently, our research has primarily focused on building AI agents capable of thinking, reasoning, planning, and acting in digital and physical environments, involving text, vision, and tabular data, with applications in game agents, embodied agents, scientific agents, and beyond. Specifically, our work spans the following directions:
AI Agent
- Develop agents for Game, Embodied, Science, Medical, Education, Coding, and more.
LLM Reasoning
- Enhance reasoning and planning abilities of large model for complex long-horizon tasks.
Neuro-Symbolic
- Bridge LLMs with classical symbolic methods to enhance AI's reasoning and planning abilities.
World Model
- Help AI understand and simulate how the world changes, enabling it to make better decisions.
Tabular Data Learning
- Build Foundation Models, Multi-Modal Model, Agents, and Causal World Models for tabular data.
📰 News
- [2026/06]: One Paper is accepted by ECCV 2026!
- [2026/05]: We won the championship in the CVPR 2026 EmbodiedBench Challenge!
- [2026/05]: Two Papers are accepted by KDD 2026!
- [2026/05]: Seven Papers are accepted by ICML 2026!
- [2026/05]: One Paper is accepted by IJCAI 2026!
- [2026/04]: Two Papers are accepted by ACL 2026!
- [2026/01]: Three Papers are accepted by ICLR 2026!
- [2026/01]: Congratulations on winning the Best Student Paper Award at the AAAI 2026 Trust Agent Workshop!
- [2026/01]: One Paper is accepted by WWW 2026!
- [2025/11]: One Paper is accepted by AAAI 2026!
- [2025/11]: One Paper is accepted by AAAI 2026 Trust Agent Workshop!
- [2025/10]: Congratulations to the three students (Hao-Zhe Tan, Zi-Jian Cheng, Song-Lin Lv) who received the National Scholarship!
- [2025/09]: One Paper is accepted by NeurIPS 2025!
- [2025/08]: One Paper is accepted by EMNLP 2025!
- [2025/05]: We have released TabFSBench for evaluation tabular data learning in open environments.
- [2025/05]: Three Papers are accepted by ICML 2025!
- [2025/04]: One Paper is accepted by IJCAI 2025 Survey Track!
- [2025/01]: One Paper is accepted by ICLR 2025!
- [2024/12]: We have released ChinaTravel benchmark for travel planning.
- [2024/12]: One Paper is accepted by AAAI 2025!
- [2024/10]: We have released Awesome Neuro-Symbolic Learning in the Era of Foundation Models.
- [2024/05]: One Paper is accepted by FCS!
- [2024/05]: One Paper is accepted by KDD 2024!
- [2024/04]: One Paper is accepted by ICML 2024!
- [2024/01]: One Paper is accepted by ICLR 2024!
- [2023/12]: CFP: We are organizing a "Robust Machine Learning in Open Environments" workshop in PAKDD 2024, Taipei, May 7, 2024
- [2023/12]: One Paper is accepted by IEEE TVCG!
- [2023/11]: One paper is accepted by Science China Information Science!
- [2023/05]: We open-sourced a LLM for Chinese Legal domain LawGPT.⛏️ 🛠️
- [2022/07]: We open-sourced the semi-supervised learning toolkit LAMDA-SSL.⛏️ 🛠️