I am a first-year Ph.D. student at the Institute for Artificial Intelligence, Peking University, advised by Prof. Song-Chun Zhu. My research explores multi-agent decision making, empathetic cooperation, and social intelligence. I am also a research intern in the Multi-Agent System Lab at the Beijing Institute for General Artificial Intelligence (BIGAI), where I build learning algorithms for mixed-motive environments. Previously, I completed my B.S. in Automation at Tsinghua University (GPA 3.78/4.00).
Research interests: multi-agent reinforcement learning, social intelligence, large language model agents
Email: kfq20@stu.pku.edu.cn · Phone: (+86) 173-5819-0815 · Location: Beijing, China
🔥 News
- 2025.09: 🎉 Awarded the National Scholarship at Peking University.
- 2024.09: ✨ Started my Ph.D. at Peking University and began serving as Head of the Academic Department, School of Intelligence Science and Technology.
- 2023.12: 🏆 Our team finished 6/117 (Honorable Winner) in the NeurIPS 2023 Melting Pot Contest.
📝 Publications
Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games
Fanqi Kong, Yizhe Huang, Song-Chun Zhu, Siyuan Qi, Xue Feng
Paper · Code · Dataset
- Empathetic policy learning framework that adapts cooperation dynamics in mixed-motive games.
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
Yizhe Huang, Xingbo Wang, Hao Liu, Fanqi Kong, Aoyang Qin, Min Tang, Xiaoxi Wang, Song-Chun Zhu, Mingjie Bi, Siyuan Qi, et al.
Paper · Code · Dataset
- Introduces a configurable benchmark with dynamic social roles for evaluating cooperative intelligence.
Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
Yizhe Huang, Anji Liu, Fanqi Kong, Yaodong Yang, Song-Chun Zhu, Xue Feng
Paper · Code
- Two-tier opponent modeling that accelerates adaptation under shifting cooperative incentives.
Enhancing LLM-Based Social Bot via an Adversarial Learning Framework
Fanqi Kong, Xiaoyuan Zhang, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng
Paper · Code · Dataset
Oral Presentation
- Adversarial training pipeline that strengthens conversational robustness and social reasoning in LLM agents.
🧪 Preprints
SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
Fanqi Kong, Weiqin Zu, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng
Paper · Code · Dataset
- Benchmark focused on multimodal social interaction comprehension and causal reasoning in videos.
Adaptive Punishment for Cooperation in Mixed-Motive Games
Min Tang, Fanqi Kong, Linyuan Lu, Xue Feng
Paper · Code
- Investigates adaptive sanction mechanisms that stabilize cooperation under strategic incentives.
AEGIS: Automated Error Generation and Identification for Multi-Agent Systems
Fanqi Kong, Ruijie Zhang, Huaxiao Yin, Guibin Zhang, Xiaofei Zhang, Ziang Chen, Zhaowei Zhang, Xiaoyuan Zhang, Song-Chun Zhu, Xue Feng
Paper · Code
- Automated pipeline that stress-tests multi-agent deployments by synthesizing diverse failure scenarios.
ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspective
Yiwen Zhang, Ziang Chen, Fanqi Kong, Yizhe Huang, Xue Feng
Paper · Code
- Teaches large language models theory-of-mind planning skills through multi-agent policy optimization.
🏆 Honors and Awards
- 2025 — National Scholarship, Peking University.
- 2024 — Lixin Scholarship, School of Intelligence Science and Technology, Peking University.
- 2024 — Outstanding Graduate, Department of Automation, Tsinghua University.
- 2023 — Friend of Tsinghua – Hande Scholarship.
- 2023 — Tsinghua University Scholarship (Excellence in Arts and Literature).
- 2023 — Person of the Year, Department of Automation, Tsinghua University.
- 2021 — Tsinghua University Scholarship (Excellence in Social Work).
🎓 Education
- 2024 – Present — Ph.D., Institute for Artificial Intelligence, Peking University. Advisor: Prof. Song-Chun Zhu.
- 2020 – 2024 — B.S., Department of Automation, Tsinghua University. GPA: 3.78/4.00.
💼 Research Experience
- 2023 – Present — Research Intern, Multi-Agent System Lab, Beijing Institute for General Artificial Intelligence (BIGAI). Developing algorithms for multi-agent decision making and empathetic cooperation.
🤝 Leadership and Service
- 2024 – Present — Head of Academic Department, School of Intelligence Science and Technology, Peking University.
- 2023 – 2024 — Presidium Member, Student Union, Department of Automation, Tsinghua University.
- 2022 – 2023 — Head of Arts Department, Student Union, Department of Automation, Tsinghua University.
🎮 Competitions
- 2023 — NeurIPS Melting Pot Contest, Honorable Winner (6/117). Core contributor on mixed-motive multi-agent cooperation tasks.