Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
This addresses the reliability of multi-agent AI systems for applications like cultural sensitivity in chatbots and group decision-making simulations, but it is incremental as it identifies limitations without proposing solutions.
The study investigated whether LLM agents can reliably adopt assigned personas in multi-agent collaboration, finding that while such discussions can enhance diverse perspectives, agents often exhibit conformity and persona inconsistency, especially when debate is encouraged.
Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural sensitivity of the chatbot's responses. These applications, however, are predicated on the ability of AI agents to reliably adopt assigned personas and mimic human interactions. To see whether LLM agents satisfy these requirements, we examine AI agent ensembles engaged in cross-national collaboration and debate by analyzing their private responses and chat transcripts. Our findings suggest that multi-agent discussions can support collective AI decisions that more often reflect diverse perspectives, yet this effect is tempered by the agents' susceptibility to conformity due to perceived peer pressure and occasional challenges in maintaining consistent personas and opinions. Instructions that encourage debate in support of one's opinions rather than collaboration increase the rate of inconstancy. Without addressing the factors we identify, the full potential of multi-agent frameworks for producing more culturally diverse AI outputs or more realistic simulations of group decision-making may remain untapped.