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

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.

💡 Research Summary

The paper addresses the emerging problem of cooperation collapse in multi‑agent systems (MAS) powered by large language models (LLMs). Drawing on the well‑established role of reputation in human societies and traditional MAS, the authors propose RepuNet, a dual‑level reputation framework that operates both at the agent level (self‑ and peer‑reputation updates) and at the system level (network rewiring based on reputation scores). Agents interact through direct encounters and indirect gossip; after each encounter they invoke an LLM‑based “ShapeRepuPeer” prompt to generate or update a natural‑language reputation description and a quantitative score μ in the range