Shuyue Hu

Shuyue Hu

Auto-generated profile, based on publicly available information

Shuyue Hu

Shanghai AI Laboratory, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 June 2025 in Science China Information Sciences
Verified
Journal Article
Closed access
PDF file
JLJinzhuo Liu
Jinzhuo Liu
GJGuangchen Jiang
Guangchen Jiang
CCChen Chu
Chen Chu
YLYong Li
Yong Li
ZWZhen Wang
Zhen Wang
SHShuyue Hu
Shuyue Hu

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZWZhen Wang
Zhen Wang
ZSZhao Song
Zhao Song
CSChen Shen
Chen Shen
SHShuyue Hu
Shuyue Hu
Altruistic punishment (or punishment) has been extensively shown as an important mechanism for promoting cooperation in human societies. In AI, the emergence of punishment has received much recent interest. In this paper, we contribute with a novel evolutionary game theoretic model to study the impacts of environmental feedback. Whereas a population of agents plays public goods games, there exists a third-party population whose payoffs depend not only on whether to punish or not, but also on the state of the environment (e.g., how cooperative the agents in a social dilemma are). Focusing on one-shot public goods games, we show that environmental feedback, by itself, can lead to the emergence of punishment. We analyze the co-evolution of punishment and cooperation, and derive conditions for their co-presence, co-dominance and co-extinction. Moreover, we show that the system can exhibit bistability as well as cyclic dynamics. Our findings provide a new explanation for the emergence of punishment. On the other hand, our results also alert the need for careful design of implementing punishment in multi-agent systems, as the resulting evolutionary dynamics can be somewhat complex.

21 November 2025
Verified
Conference Paper
Open access
YZYiqun Zhang
Yiqun Zhang
HLHao Li
Hao Li
JCJianhao Chen
Jianhao Chen
HZHangfan Zhang
Hangfan Zhang
PYPeng Ye
Peng Ye
SHShuyue Hu
Shuyue Hu

1 August 2024
Verified
Conference Paper
Open access
PDF file
SRSiyue Ren
Siyue Ren
ZCZhiyao Cui
Zhiyao Cui
RSRuiqi Song
Ruiqi Song
ZWZhen Wang
Zhen Wang
SHShuyue Hu
Shuyue Hu
Social norms play a crucial role in guiding agents towards understanding and adhering to standards of behavior, thus reducing social conflicts within multi-agent systems (MASs). However, current LLM-based (or generative) MASs lack the capability to be normative. In this paper, we propose a novel architecture, named CRSEC, to empower the emergence of social norms within generative MASs. Our architecture consists of four modules: Creation & Representation, Spreading, Evaluation, and Compliance. This addresses several important aspects of the emergent processes all in one: (i) where social norms come from, (ii) how they are formally represented, (iii) how they spread through agents' communications and observations, (iv) how they are examined with a sanity check and synthesized in the long term, and (v) how they are incorporated into agents' planning and actions. Our experiments deployed in the Smallville sandbox game environment demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs. The positive outcomes of our human evaluation, conducted with 30 evaluators, further affirm the effectiveness of our approach. Our project can be accessed via the following link: https://github.com/sxswz213/CRSEC.

27 November 2024 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
CSChen Shen
Chen Shen
ZHZhixue He
Zhixue He
HGHao Guo
Hao Guo
SHShuyue Hu
Shuyue Hu
JTJun Tanimoto
Jun Tanimoto
PHPetter Holme
Petter Holme
Stylized experiments, the public goods game and its variants thereof, have taught us the peculiar reproducible fact that humans tend to cooperate (or contribute to shared resources) more than expected from economically rational assumptions. There have been two competing explanations for this phenomenon: Either cooperating is an innate human trait (the prosocial preference hypothesis) or a transitory effect while learning the game (the confused learner hypothesis). We use large-scale experimental data in the two-player version of the public goods game—the prisoner’s dilemma—from an experimental design to distinguish between these two hypotheses. By monitoring the effects of zealots (persistently cooperating bots) and varying the participants’ awareness of them, we find a considerably more complex scenario than previously reported. People indeed have a prosocial bias, but not to the degree that they always forego taking action to increase their profit. While our findings end the simplistic theorizing of prosociality, an observed positive, cooperative response to zealots has actionable policy implications.

3 January 2025 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
JSJuan Shi
Juan Shi
CCChen Chu
Chen Chu
GFGuoxi Fan
Guoxi Fan
DHDie Hu
Die Hu
JLJinzhou Liu
Jinzhou Liu
SHShuyue Hu
Shuyue Hu
In this article, we introduce a new theory for payoff control in multichannel learning environments, where agents interact with each other over multiple channels and each channel is a repeated normal form game. We propose two payoff control strategies—partial control and full control—that allow a single agent to set an upper bound to the opponent’s expected payoffs summed across all channels, even if the opponent is a reinforcement learning agent. We prove that a partial (or full) control strategy can be obtained by solving a system of inequalities, and characterize the conditions under which such a partial (or full) control strategy exists. We show that by utilizing these control strategies, the agent can influence the opponent’s learning evolution and direct it toward a desired viable equilibrium. Our experiments confirm the effectiveness of our theory for payoff control in a wide range of multichannel learning environments.