😀 About Me
I am a researcher at the Multi-Agent System Lab, Beijing Institute for General Artificial Intelligence. My research interests include multi-agent systems, reinforcement learning, large language models, and spatio-temporal data mining.
I received my Ph.D. in Computer Science and Engineering from the Hong Kong University of Science and Technology under the supervision of Prof. Qiang Yang
and Dr. Yu Zheng. My work has been published in top-tier conferences such as ICML, ICLR, ACL, KDD, WWW, AAAI, and CIKM, as well as leading journals including TKDE, Transportation Research Part C.
- An interest in Large language models & Reinforcement learning
- Strong code ability
- Determination to do high-quality research
🔥 News
• 2026.05 🎉 One paper has been accepted in ICML 2026.
• 2026.01 🎉 One paper has been accepted in ICLR 2026.
• 2026.01 🎉 One paper has been accepted in WWW 2026.
• 2025.11 🎉 One paper has been accepted in SIGKDD 2026.
• 2025.11 🎉 One paper has been accepted in AAAI 2026.
• 2026.01 - 2028.12 🎉 National Natural Science Foundation of China
• 2025.05 🎉 Two papers have been accepted in ACL 2025.
📝 Selected Publications
§ Equal contribution ✉ Corresponding authors
2026
-
Yuanhao Zeng, Ao Lu, Lufei Li, Zheng Zhang,
Yexin Li✉, Kan Ren ✉. Large Language Models Explore by Latent Distilling. ICML 2026 -
Yexin Li. CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning. TMLR 2026 -
Zheng Zhang, Ziwei Shan, Kaitao Song,
Yexin Li✉, Kan Ren ✉. Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning. ICLR 2026 -
Jinjin Guo,
Yexin Li✉, Zhichao Huang, Jun Fang, Zhiyuan Liu, C. Liu, et al. Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning. WWW 2026 -
Sijie Ruan, Renchi Jiang, Song Tang,
Yexin Li, Weixin Zhai, Xinhao Liu, Bingbing Hu, Hanning Yuan, Caicong Wu, Shuliang Wang. Predictive Mobile Refueling for Agricultural Machinery via Deep Reinforcement Learning. SIGKDD 2026 -
Zhixiang Zhang, Shuo Chen,
Yexin Li, Feng Wang. ADAPT: Adaptive Decentralized Architecture with Perception-Aligned Training for Structural Generalization in Multi-Agent RL. AAAI 2026
2025
-
Zheng Zhang, Shaocheng Lan, Lei Song, Jiang Bian,
Yexin Li, Kan Ren. Learning to Select In-Context Demonstration Preferred by Large Language Model. ACL Findings 2025 -
Yipeng Kang, Junqi Wang,
Yexin Li, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, et al. Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective. ACL Findings 2025
2024
-
Yexin Li, Zhancun Mu, Siyuan Qi. A Contextual Combinatorial Bandit Approach to Negotiation. ICML 2024 -
Siyuan Qi §, Shuo Chen §,
Yexin Li§, Xiangyu Kong §, Junqi Wang §, Bangcheng Yang, Pring Wong, et al. CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents. ICLR 2024
2023
-
Siyuan Feng, Shuqing Wei, Junbo Zhang,
Yexin Li, Jintao Ke, Gaode Chen, Yu Zheng, Hai Yang. A Macro–Micro Spatio-temporal Neural Network for Traffic Prediction. TRC 2023 -
Tianfu He, Jie Bao,
Yexin Li, Hui He, Yu Zheng. Crowd-Sensing Enhanced Parking Patrol Using Sharing Bikes' Trajectories. TKDE 2021 -
Yexin Li, Yu Zheng, Qiang Yang. Cooperative Multi-Agent Reinforcement Learning in Express System. CIKM 2020 -
Ting Li, Junbo Zhang, Kainan Bao, Yuxuan Liang,
Yexin Li, Yu Zheng. AutoST: Efficient Neural Architecture Search for Spatio-temporal Prediction. SIGKDD 2020 -
Yexin Li, Yu Zheng, Qiang Yang. Efficient and Effective Express via Contextual Cooperative Reinforcement Learning. SIGKDD 2019 -
Yexin Li, Yu Zheng. Citywide Bike Usage Prediction in a Bike-Sharing System. TKDE 2019 -
Yexin Li, Y. Zheng, et al. Dynamic Bike Reposition: A Spatio-Temporal Reinforcement Learning Approach. SIGKDD 2018 -
Yexin Li, Yu Zheng, Huichu Zhang, Lei Chen. Traffic Prediction in a Bike-Sharing System. SIGSPATIAL 2015
🎓 Education
- 2016.09 - 2020.11 - Ph.D. in Computer Science and Engineering, Hong Kong University of Science and Technology
- 2013.09 - 2015.08 - MPhil in Computer Science and Engineering, Hong Kong University of Science and Technology
- 2009.09 - 2013.07 - B.S. in Mathematics and Applied Mathematics, Xi'an Jiaotong University
💼 Work Experience
- 2023.04 - 2026.04 - Researcher at the Multi-Agent Systems Lab, Beijing Institute for General Artificial Intelligence
- 2021.01 - 2023.03 - Doctor Management Trainee at JD.COM
- 2017.05 - 2018.01 - Research Intern at Microsoft Research Asia
🤝 Collaborators
- Sijie Ruan - Assistant professor at School of Computer Science and Technology, Beijing Institute of Technology
- Yuhan Zhao - Researcher at Multi-Agent System Lab, Beijing Institute for General Artificial Intelligence
- Shuo Chen - Researcher at Multi-Agent System Lab, Beijing Institute for General Artificial Intelligence
- Siyuan Qi - Researcher at Multi-Agent System Lab, Beijing Institute for General Artificial Intelligence
- Jinjin Guo - Algorithm Engineer at JD.COM