A Reputation System for Large Language Model-based Multi-agent Systems to Avoid the Tragedy of the Commons

2025-05-08

AI Summary

In large language model (LLM)-based multi-agent systems, self-interested agent behavior leads to the “tragedy of the commons.” Method: We propose RepuNet, a two-tier reputation mechanism that models reputation dynamics through both direct interactions and indirect gossip propagation, enabling agents to autonomously form or sever connections to restructure their interaction network. Our approach integrates LLM-driven multi-agent simulation, dynamic graph neural networks, reputation diffusion algorithms, and game-theoretic incentive design. Contribution/Results: We empirically demonstrate, for the first time, that reputation systems can spontaneously induce key socio-emergent phenomena—including cooperative cluster formation, exploiter isolation, and preferential propagation of positive gossip. Experiments across two canonical scenarios show that RepuNet significantly improves long-term cooperation rates and suppresses the spread of selfish strategies, thereby robustly stabilizing pro-social network structures and healthy information ecosystems.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The tragedy of the commons, where individual self-interest leads to collectively disastrous outcomes, is a pervasive challenge in human society. Recent studies have demonstrated that similar phenomena can arise in generative multi-agent systems (MASs). To address this challenge, this paper explores the use of reputation systems as a remedy. We propose RepuNet, a dynamic, dual-level reputation framework that models both agent-level reputation dynamics and system-level network evolution. Specifically, driven by direct interactions and indirect gossip, agents form reputations for both themselves and their peers, and decide whether to connect or disconnect other agents for future interactions. Through two distinct scenarios, we show that RepuNet effectively mitigates the 'tragedy of the commons', promoting and sustaining cooperation in generative MASs. Moreover, we find that reputation systems can give rise to rich emergent behaviors in generative MASs, such as the formation of cooperative clusters, the social isolation of exploitative agents, and the preference for sharing positive gossip rather than negative ones.

Problem

• Addressing tragedy of the commons in multi-agent systems
• Proposing RepuNet for dynamic reputation management
• Promoting cooperation and mitigating selfish behaviors

Innovation

• RepuNet: dynamic dual-level reputation framework
• Agent-level and system-level reputation modeling
• Direct interactions and indirect gossip drive reputations