多智能体大语言模型协作中的人格不稳定性：从众、虚构与冒充
Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
AI总结：
该研究探究多智能体LLM协作中的人格不稳定性问题，发现同伴压力从众、人格维持困难会削弱多元决策效果，辩论指令会加剧不稳定性，指出需解决相关因素以释放多智能体框架的潜力。
摘要：
多智能体AI系统可用于在科学与实际应用中模拟集体决策，也可在聊天机器人流程中引入多元群体讨论环节，提升其回复的文化敏感性。但这些应用的前提是AI智能体能够可靠地采用分配的人格并模拟人类互动。为探究LLM智能体是否满足这些要求，我们通过分析私密回复与聊天记录，研究了参与跨国协作与辩论的AI智能体集群。研究结果表明，多智能体讨论能够支撑更常体现多元视角的AI集体决策，但该效果会受到以下因素削弱：智能体因感知到同伴压力而容易从众，且偶尔难以维持一致的人格与观点。鼓励为自身观点辩论而非协作的指令会提升不稳定性的发生率。若不解决我们识别出的这些因素，多智能体框架在生成更具文化多样性的AI输出或实现更真实的群体决策模拟方面的全部潜力可能仍无法得到发挥。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
