Shuyue Hu

Profile

I’m a researcher at Shanghai Artificial Intelligence Laboratory, Shanghai, China. My research focuses on multi-agent systems, game theory, and large language models. Recently, I am particularly interested in how we can boost the performance of large language models through the lens of multi-agent systems.

Publications

Payoff Control in Multichannel Games: Influencing Opponent Learning Evolution

Juan Shi, Chen Chu, Guoxi Fan, Die Hu, Jinzhuo Liu, Zhen Wang, Shuyue Hu

IEEE Transactions on Cybernetics 2025

ABS
Understanding When and Why Graph Attention Mechanisms Work via Node Classification

Understanding When and Why Graph Attention Mechanisms Work via Node Classification

Zhongtian Ma, Qiaosheng Zhang, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang

ABSHTMLPDF
Beyond a binary theorizing of prosociality

Beyond a binary theorizing of prosociality

Chen Shen, Zhixue He, Hao Guo, Shuyue Hu, Jun Tanimoto, Lei Shi, Petter Holme

Proceedings of the National Academy of Sciences of the United States of America 2024

ABSHTMLPDF
OASIS: Open Agent Social Interaction Simulations with One Million Agents

OASIS: Open Agent Social Interaction Simulations with One Million Agents

Ziyi Yang, Zaibin Zhang, Zirui Zheng, Yuxian Jiang, Ziyue Gan, Zhiyu Wang, Zijian Ling, Jinsong Chen, Martz Ma, Bowen Dong, Prateek Gupta, Shuyue Hu, Zhenfei Yin, G. Li, Xu Jia, Lijun Wang, Bernard Ghanem, Huchuan Lu, Wanli Ouyang, Yu Qiao, Philip Torr, Jing Shao

arXiv.org 2024

ABSHTMLPDF
Large Language Models Overcome the Machine Penalty When Acting Fairly but Not When Acting Selfishly or Altruistically

Large Language Models Overcome the Machine Penalty When Acting Fairly but Not When Acting Selfishly or Altruistically

Zhen Wang, Ruiqi Song, Chen Shen, Shiya Yin, Zhao Song, B. Battu, Lei Shi, Danyang Jia, Talal Rahwan, Shuyue Hu

arXiv.org 2024

ABSHTMLPDF
Emergence of Social Norms in Large Language Model-based Agent Societies

Emergence of Social Norms in Large Language Model-based Agent Societies

Siyue Ren, Zhiyao Cui, Ruiqi Song, Zhen Wang, Shuyue Hu

International Joint Conference on Artificial Intelligence 2024

ABS
A Successful Strategy for Multichannel Iterated Prisoner's Dilemma

A Successful Strategy for Multichannel Iterated Prisoner's Dilemma

Zhen Wang, Zhaoheng Cao, Juan Shi, Peican Zhu, Shuyue Hu, Chen Chu

International Joint Conference on Artificial Intelligence 2024

ABS
Configurable Mirror Descent: Towards a Unification of Decision Making

Configurable Mirror Descent: Towards a Unification of Decision Making

Pengdeng Li, Shuxin Li, Chang Yang, Xinrun Wang, Shuyue Hu, Xiao Huang, Hau Chan, Bo An

International Conference on Machine Learning 2024

ABSHTMLPDF
Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning

Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning

Qiaosheng Zhang, Chenjia Bai, Shuyue Hu, Zhen Wang, Xuelong Li

arXiv.org 2024

ABSPDF
Emergence of Social Norms in Generative Agent Societies: Principles and Architecture

Emergence of Social Norms in Generative Agent Societies: Principles and Architecture

Siyue Ren, Zhiyao Cui, Ruiqi Song, Zhen Wang, Shuyue Hu

International Joint Conference on Artificial Intelligence 2024

ABSHTMLPDF
Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas

Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas

Hao Guo, Chunjiang Mu, Yang Chen, Chen Shen, Shuyue Hu, Zhen Wang

Neurocomputing 2024

ABSHTMLPDF
The Stochastic Evolutionary Dynamics of Softmax Policy Gradient in Games

The Stochastic Evolutionary Dynamics of Softmax Policy Gradient in Games

Chin-wing Leung, Shuyue Hu, Ho-fung Leung

Autonomous Agents Agents and Multi-Agent Systems 2024

ABS
The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium

The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium

Shuyue Hu, Harold Soh, Georgios Piliouras

Neural Information Processing Systems 2023

How committed individuals shape social dynamics: A survey on coordination games and social dilemma games

Chen Shen, Hao Guo, Shuyue Hu, Lei Shi, Zhen Wang, J. Tanimoto

Europhysics letters 2023

ABSPDF
Facilitating cooperation in human-agent hybrid populations through autonomous agents

Facilitating cooperation in human-agent hybrid populations through autonomous agents

Hao Guo, Chen Shen, Shuyue Hu, Junliang Xing, Pin Tao, Yuanchun Shi, Zhen Wang

iScience 2023

ABSHTMLPDF
A Pair-Approximation Method for Modelling the Dynamics of Multi-Agent Stochastic Games

A Pair-Approximation Method for Modelling the Dynamics of Multi-Agent Stochastic Games

Chen Chu, Zhengzhong Yuan, Shuyue Hu, Chunjiang Mu, Zhen Wang

AAAI Conference on Artificial Intelligence 2023

ABSPDF
Emergence of Punishment in Social Dilemma with Environmental Feedback

Emergence of Punishment in Social Dilemma with Environmental Feedback

Zhen Wang, Z. Song, Chen Shen, Shuyue Hu

AAAI Conference on Artificial Intelligence 2023

ABSPDF

博弈智能的研究与应用

Jianye Hao, Kun Shao, Kai Li, Dong Li, Hangyu Mao, Shuyue Hu, Zhen Wang

Scientia Sinica Informationis 2023

ABS
Heterogeneous Beliefs and Multi-Population Learning in Network Games

Heterogeneous Beliefs and Multi-Population Learning in Network Games

Shuyue Hu, Harold Soh, G. Piliouras

arXiv.org 2023

ABSPDF

Learning by reusing previous advice: a memory-based teacher–student framework

Changxi Zhu, Y. Cai, Shuyue Hu, Ho-fung Leung, Dickson K. W. Chiu

Autonomous Agents and Multi-Agent Systems 2022

ABS
Modelling the Dynamics of Regret Minimization in Large Agent Populations: a Master Equation Approach

Modelling the Dynamics of Regret Minimization in Large Agent Populations: a Master Equation Approach

Zhen Wang, Chunjiang Mu, Shuyue Hu, Chen Chu, Xuelong Li

International Joint Conference on Artificial Intelligence 2022

ABSPDF
Modelling the Dynamics of Multi-Agent Q-learning: The Stochastic Effects of Local Interaction and Incomplete Information

Modelling the Dynamics of Multi-Agent Q-learning: The Stochastic Effects of Local Interaction and Incomplete Information

Chin-wing Leung, Shuyue Hu, Ho-fung Leung

International Joint Conference on Artificial Intelligence 2022

ABSPDF
A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs

A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs

Chen Chu, Yong Li, Jinzhuo Liu, Shuyue Hu, Xuelong Li, Zhen Wang

International Joint Conference on Artificial Intelligence 2022

ABSPDF
The Dynamics of Q-learning in Population Games: a Physics-Inspired Continuity Equation Model

The Dynamics of Q-learning in Population Games: a Physics-Inspired Continuity Equation Model

Shuyue Hu, Chin-wing Leung, Ho-fung Leung, Harold Soh

Adaptive Agents and Multi-Agent Systems 2022

ABSPDF
Individual-Level Inverse Reinforcement Learning for Mean Field Games

Individual-Level Inverse Reinforcement Learning for Mean Field Games

Yang Chen, Libo Zhang, Jiamou Liu, Shuyue Hu

Adaptive Agents and Multi-Agent Systems 2022

ABSPDF

Formal Modeling of Reinforcement Learning with Many Agents through Repeated Local Interactions

Chin-wing Leung, Shuyue Hu, Ho-fung Leung

IEEE International Conference on Tools with Artificial Intelligence 2021

ABS
Gist Trace-based Learning: Efficient Convention Emergence from Multilateral Interactions

Gist Trace-based Learning: Efficient Convention Emergence from Multilateral Interactions

Shuyue Hu, Chin-wing Leung, Ho-fung Leung, Jiamou Liu

ACM Transactions on Autonomous and Adaptive Systems 2021

ABS
A Theoretical Framework for Large-Scale Human-Robot Interaction with Groups of Learning Agents

A Theoretical Framework for Large-Scale Human-Robot Interaction with Groups of Learning Agents

Nicholas Teh, Shuyue Hu, Harold Soh

IEEE/ACM International Conference on Human-Robot Interaction 2021

ABSPDF
Self-Play or Group Practice: Learning to Play Alternating Markov Game in Multi-Agent System

Self-Play or Group Practice: Learning to Play Alternating Markov Game in Multi-Agent System

Chin-wing Leung, Shuyue Hu, Ho-fung Leung

International Conference on Pattern Recognition 2021

ABS
A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint

A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint

Changxi Zhu, Ho-fung Leung, Shuyue Hu, Yi Cai

ACM Transactions on Autonomous and Adaptive Systems 2020

ABSPDF
Learning by Reusing Previous Advice in Teacher-Student Paradigm

Learning by Reusing Previous Advice in Teacher-Student Paradigm

Changxi Zhu, Yi Cai, Ho-fung Leung, Shuyue Hu

Autonomous Agents and Multi-Agent Systems 2020

The Evolutionary Dynamics of Independent Learning Agents in Population Games

The Evolutionary Dynamics of Independent Learning Agents in Population Games

Shuyue Hu, Chin-wing Leung, Ho-fung Leung, Harold Soh

arXiv.org 2020

ABSPDF
Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach

Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach

Shuyue Hu, Chin-wing Leung, Ho-fung Leung

Neural Information Processing Systems 2019

Modeling Convention Emergence by Observation with Memorization

Chin-wing Leung, Shuyue Hu, Ho-fung Leung

Pacific Rim International Conference on Artificial Intelligence 2019

ABS
A Q-values Sharing Framework for Multiple Independent Q-learners

A Q-values Sharing Framework for Multiple Independent Q-learners

Changxi Zhu, Ho-fung Leung, Shuyue Hu, Y. Cai

Adaptive Agents and Multi-Agent Systems 2019

To be Big Picture Thinker or Detail-Oriented?: Utilizing Perceived Gist Information to Achieve Efficient Convention Emergence with Bilateralism and Multilateralism

To be Big Picture Thinker or Detail-Oriented?: Utilizing Perceived Gist Information to Achieve Efficient Convention Emergence with Bilateralism and Multilateralism

Shuyue Hu, Chin-wing Leung, Ho-fung Leung, J. Liu

Adaptive Agents and Multi-Agent Systems 2019

Compromise as a Way to Promote Convention Emergence and to Reduce Social Unfairness in Multi-Agent Systems

Shuyue Hu, Ho-fung Leung

Australasian Conference on Artificial Intelligence 2018

ABS
Do Social Norms Emerge? The Evolution of Agents' Decisions with the Awareness of Social Values under Iterated Prisoner's Dilemma

Do Social Norms Emerge? The Evolution of Agents' Decisions with the Awareness of Social Values under Iterated Prisoner's Dilemma

Shuyue Hu, Ho-fung Leung

IEEE International Conference on Self-Adaptive and Self-Organizing Systems 2018

ABS
Achieving Coordination in Multi-Agent Systems by Stable Local Conventions under Community Networks

Achieving Coordination in Multi-Agent Systems by Stable Local Conventions under Community Networks

Shuyue Hu, Ho-fung Leung

International Joint Conference on Artificial Intelligence 2017

ABSPDF