Welcome to Bin Zhang’s Personal Homepage!

I am an Assistant Research Fellow/Postdoctoral Researcher at the Institute of Automation, Chinese Academy of Sciences (CASIA, 中国科学院自动化研究所), working in the Key Laboratory of Cognition and Decision Intelligence for Complex Systems. Advised by Prof. Guoliang Fan (范国梁), my research spans ​​Reinforcement Learning (RL)​​, ​​Multi-agent Systems​​, and ​​Large Language Model (LLM) Agents​​, with a focus on:

• Developing ​​adaptive AI algorithms​​ for multi-agent cooperation/competition in complex environments.
• Advancing ​​LLM agents’ collaborative reasoning​​ and ​​tool-learning capabilities​​ for autonomous systems.

I also work closely with Prof. Zhiwei Xu (徐志伟) (Assistant Professor, Shandong University). And I have published 20+ papers at the international AI conferences.

If you are interested with my experience or research. Plese feel free to contact with me via Email or Wechat.

🔥 News

• 2025.04:  🎉🎉 One paper has been accepted by ICML 2025!
• 2025.04:  🎉🎉 One paper has been accepted by IJCNN 2025!
• 2025.02:  🎉🎉 One paper has been accepted by TMLR & ICLR 2025 Workshop on DATA-FM!
• 2025.01:  🎉🎉 One paper with co-first authorship has been accepted by DASFAA 2025!
• 2024.12:  🎉🎉 One paper has been accepted by AAMAS 2025!
• 2024.12:  🎉🎉 One paper has been accepted by AAAI 2025!
• 2024.10:  🎉🎉 One paper with co-first authorship has been accepted by EMNLP 2024 Industry Track!
• 2024.08:  🎉🎉 Two papers have been accepted by ICONIP 2024!
• 2024.05:  🎉🎉 One first-author paper has been accepted by ICML 2024!
• 2024.04:  🎉🎉 One paper has been accepted by IJCAI 2024!
• 2024.03:  🎉🎉 One paper has been accepted by IJCNN 2024!
• 2024.02:  🎉🎉 One first-author paper has been accepted by ICLR 2024 Workshop on LLM Agents!
• 2024.02:  🎉🎉 One paper with co-first authorship has been accepted by ICLR 2024 Workshop on LLM Agents!
• 2023.12:  🎉🎉 Two papers have been accepted by AAMAS 2024!
• 2023.12:  🎉🎉 One paper has been accepted accepted by ICASSP 2024!
• 2023.09:  🎉🎉 One paper has been accepted by NeurIPS 2023!
• 2023.04:  🎉🎉 One first-author paper has been accepted by IJCAI 2023!

📖 Educations

• 2020.09 - 2025.06              Ph.D. Candidate in Institute of Automation, Chinese Academy of Sciences
• 2016.09 - 2020.06              B.E. in School of Control Science and Engineering, Shandong University

💬 Research Interest

• Reinforcement Learning
• Multi-agent Coordination
• LLM agents (Tool Learning, Text-to-SQL, Text-based Game)

📝 Publications

NIPS 2023 Workshop

Tptu: Task planning and tool usage of large language model-based ai agents

Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao

Project

• We propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems.

arXiv:2403.02951

Benchmarking the text-to-sql capability of large language models: A comprehensive evaluation

Bin Zhang, Yuxiao Ye, Guoqing Du, Xiaoru Hu, Zhishuai Li, Sun Yang, Chi Harold Liu, Rui Zhao, Ziyue Li, Hangyu Mao

Project

• We evaluate LLMs through five Text-to-SQL related tasks, reveal performance differences and suggest task-specific optimization strategies.

• ICML 2025 Reidentify:Context-AwareIdentityGenerationforContextual Multi-AgentReinforcementLearning. Zhiwei Xu, Kun Hu, Xin Xin, Weiliang Meng, Yiwei Shi, Hangyu Mao, Bin Zhang, Dapeng Li, Jiangjin Yin
• IJCNN 2025 Enhancing Branching Policy Generalization through Self-Supervised Adversarial Instance Augmentation. Ce Zhang, Bin Zhang, Guoliang Fan
• DASFAA 2025 PET-SQL: A Prompt-enhanced Two-stage Text-to-SQL Framework with Cross-consistency. Zhishuai Li, Xiang Wang, Jingjing Zhao, Sun Yang, Guoqing Du, Xiaoru Hu, Bin Zhang, Yuxiao Ye, Ziyue Li, Rui Zhao, Hangyu Mao
• AAMAS 2025 Unveiling Decision Intention for Cooperative Multi-Agent Reinforcement Learning. Zeren Zhang, Zhiwei Xu, Guangchong Zhou, Dapeng Li, Bin Zhang, Guoliang Fan
• AAAI 2025 Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation. Dapeng Li, Na Lou, Zhiwei Xu, Bin Zhang, Guoliang Fan
• ICML 2024 Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems. Bin Zhang, Hangyu Mao, Lijuan Li, Zhiwei Xu, Dapeng Li, Rui Zhao, and Guoliang Fan
• IJCAI 2024 PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning. Yiqun Chen, Hangyu Mao, Jiaxin Mao, Shiguang Wu, Tianle Zhang, Bin Zhang, Wei Yang, Hongxing Chang
• ICLR 2024 Workshop on LLM Agents Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach. Bin Zhang, Hangyu Mao, Jingqing Ruan, et al.
• EMNLP 2024 Industry Track Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems. Yilun Kong, Jingqing Ruan, Yihong Chen, Bin Zhang, et al.
• IJCNN 2024 SGCD: Subgroup Contribution Decomposition for Multi-Agent Reinforcement Learning. Hao Chen, Bin Zhang, Guoliang Fan.
• AAMAS 2024 PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning. Hangyu Mao, Rui Zhao, Ziyue Li, Zhiwei Xu, Hao Chen, Yiqun Chen, Bin Zhang, et al.
• AAMAS Extended Abstract 2024 From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL. Dapeng Li, Zhiwei Xu, Bin Zhang, and Guoliang Fan.
• ICASSP 2024 Adaptive Parameter Sharing for Multi-Agent Reinforcement Learning. Dapeng Li, Na Lou, Bin Zhang, Zhiwei Xu, Guoliang Fan
• ICONIP 2024 Decentralized Extension for Centralized Multi-Agent Reinforcement Learning via Online Distillation. Zeren Zhang, Bin Zhang, Guangchong Zhou, Dapeng Li, Zhiwei Xu and Guoliang Fan
• ICONIP 2024 GATE: Guided Contrastive State Space for Multi-Agent Reinforcement Learning. Hao Chen, Bin Zhang and Guoliang Fan
• NeurIPS 2023 Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL. Zhiwei Xu, Bin Zhang, Dapeng Li, Guangchong Zhou, Zeren Zhang, Guoliang Fan
• IJCAI 2023 Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning. Bin Zhang, Lijuan Li, Zhiwei Xu, Dapeng Li, Guoliang Fan
• IJCNN 2023 SEA: A Spatially Explicit Architecture for Multi-Agent Reinforcement Learning. Dapeng Li, Zhiwei Xu, Bin Zhang, Guoliang Fan
• AAAI 2023 Consensus Learning for Cooperative Multi-Agent Reinforcement Learning. Zhiwei Xu, Bin Zhang, Dapeng Li, Zeren Zhang, Guangchong Zhou, Hao Chen, Guoliang Fan
• AAAI 2023 HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism. Zhiwei Xu, Yunpeng Bai, Bin Zhang, Dapeng Li, and Guoliang Fan
• NeurIPS 2022 Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning. Zhiwei Xu, Dapeng Li, Bin Zhang, Yuan Zhan, Yunpeng Bai, and Guoliang Fan
• ICONIP 2022 Multi-Agent Hyper-Attention Policy Optimization. Bin Zhang, Zhiwei Xu, Yiqun Chen, Dapeng Li, Yunpeng Bai, Guoliang Fan, and Lijuan Li
• ICONIP 2022 Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Network. Bin Zhang, Yunpeng Bai, Zhiwei Xu, Dapeng Li, and Guoliang Fan
• IJCNN 2022 Cooperative Multi-agent Reinforcement Learning with Hypergraph Convolution. Yunpeng Bai, Chen Gong, Bin Zhang, Guoliang Fan, Xinwen Hou, Yu Liu
• AAMAS 2022 SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning. Zhiwei Xu, Yunpeng Bai, Dapeng Li, Bin Zhang, and Guoliang Fan
• ICONIP 2022 Learning to Coordinate via Multiple Graph Neural Networks. Zhiwei Xu, Bin Zhang, Yunpeng Bai, Dapeng Li, and Guoliang Fan

🧑‍🎨 Preprint

• arXiv:2506.12509 Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs. Jiwei Fang, Bin Zhang, Changwei Wang, Jin Wan, Zhiwei Xu
• arXiv:2504.12961 QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?. Zhouyang Jiang, Bin Zhang, Airong Wei, Zhiwei Xu
• arXiv:2403.02951 Benchmarking the text-to-sql capability of large language models: A comprehensive evaluation. Bin Zhang, Yuxiao Ye, Guoqing Du, Xiaoru Hu, Zhishuai Li, Sun Yang, Chi Harold Liu, Rui Zhao, Ziyue Li, Hangyu Mao
• Constructing Informative Subtask Representations for Multi-Agent Coordination. Guangchong Zhou, Zhiwei Xu, Bin Zhang, Dapeng Li, Zeren Zhang, Guoliang Fan
• arXiv:2408.09501 Beyond Local Views: Global State Inference with Diffusion Models for Cooperative Multi-Agent Reinforcement Learning. Zhiwei Xu, Hangyu Mao, Nianmin Zhang, Xin Xin, Pengjie Ren, Dapeng Li, Bin Zhang, Guoliang Fan, Zhumin Chen, Changwei Wang, Jiangjin Yin

🥇 Honors and Awards

• 2023, Future Star Award, SenseTime Research (Intern Top 1)
• 2023, Merit Student, University of Chinese Academy of Sciences
• 2022, Climbing Scholarship, University of Chinese Academy of Sciences
• 2020, Outstanding Graduates, Shandong Province
• 2020, Weichai Power Scholarship, Shandong University
• 2017-2019, National Scholarship, Ministry of Education (2 times)
• 2017-2020, First-class Scholarship, Shandong University (3 times)

🌠 Academic Services

Program Committee Member or Reviewer:

• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
• Applied Soft Computing Journal
• International Conference on Learning Representations (ICLR 2024)
• International Conference on Machine Learning (ICML 2024)
• AAAI Conference on Artificial Intelligence (AAAI 2025)
• International Joint Conference on Artificial Intelligence (IJCAI 2024)
• International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025)
• International World Wide Web Conference (WWW 2025)

💻 Internships

• 2023.07 - 2024.04, SenseTime Research, China.