On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
This addresses the problem of understanding and designing AI communities for researchers and developers, offering insights into value-driven collective intelligence, though it is incremental in applying existing theories to AI.
The study investigated how value diversity affects collective behavior in multi-agent LLM communities, finding that it enhances value stability and fosters emergent, creative principles, but with diminishing returns and instability at extreme heterogeneity.
As Large Language Models (LLM) based multi-agent systems become increasingly prevalent, the collective behaviors, e.g., collective intelligence, of such artificial communities have drawn growing attention. This work aims to answer a fundamental question: How does diversity of values shape the collective behavior of AI communities? Using naturalistic value elicitation grounded in the prevalent Schwartz's Theory of Basic Human Values, we constructed multi-agent simulations where communities with varying numbers of agents engaged in open-ended interactions and constitution formation. The results show that value diversity enhances value stability, fosters emergent behaviors, and brings more creative principles developed by the agents themselves without external guidance. However, these effects also show diminishing returns: extreme heterogeneity induces instability. This work positions value diversity as a new axis of future AI capability, bridging AI ability and sociological studies of institutional emergence.