Reputation as a Solution to Cooperation Collapse in LLM-based MASs

TL;DR

This paper introduces RepuNet, a dynamic reputation framework for large language model multi-agent systems, which effectively prevents cooperation collapse and fosters emergent cooperative behaviors.

Contribution

The paper presents RepuNet, a novel dual-level reputation system that models agent and network dynamics to sustain cooperation in LLM-based MASs.

Findings

RepuNet successfully prevents cooperation collapse in tested scenarios.

Reputation systems lead to formation of cooperative clusters.

Agents tend to share positive gossip over negative gossip.

Abstract

Cooperation has long been a fundamental topic in both human society and AI systems. However, recent studies indicate that the collapse of cooperation may emerge in multi-agent systems (MASs) driven by large language models (LLMs). To address this challenge, we explore 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 three distinct scenarios, we show that RepuNet effectively avoids cooperation collapse, promoting and sustaining cooperation in LLM-based MASs. Moreover, we find that reputation systems can give rise to rich emergent behaviors in LLM-based 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. The GitHub repository for our project can be accessed via the following link: https://github.com/RGB-0000FF/RepuNet.