多大模型共处时，会自发形成不同行为模式，且受身份暴露和提示设计影响。
"Who Am I, and Who Else Is Here?" Behavioral Differentiation Without Role Assignment in Multi-Agent LLM Systems
- 在统一平台中测试7个异构大模型互动，控制变量观察行为分化
- 身份公开使行为趋同，去除提示框架后差异消失，证明互动驱动分化
- 适合研究多智能体系统社会性、模型间协作机制的学者参考
当多个大型语言模型在共享对话中交互时，它们是否会发展出不同的社会角色，还是趋于行为一致？我们构建了一个受控实验平台，在统一推理后端上协调7个异构大模型进行多代理讨论，系统性地改变群体构成、命名规范和提示结构，共开展12个实验系列（208次运行，13,786条编码消息）。每条消息由来自不同模型家族的两名大模型裁判（Gemini 3.1 Pro 和 Claude Sonnet 4.6）独立标注六个行为标记，平均Cohen's kappa达0.78，采用保守交集仲裁。人类验证随机抽取的609条消息确认编码可靠性（平均kappa=0.73 vs. Gemini）。结果发现：（1）异构群体的行为分化显著高于同质群体（余弦相似度0.56对比0.85；p < 10^-5，r = 0.70）；（2）当某代理崩溃时，群体自动产生补偿性响应模式；（3）揭示真实模型名称显著提升行为一致性（余弦相似度从0.56升至0.77，p = 0.001）；（4）移除所有提示支架后，行为特征收敛至同质水平（p < 0.001）。关键在于，这些行为在孤立运行时不存在，表明行为多样性是一种由架构异质性、群体上下文与提示级支架共同驱动的结构性、可复现现象。
原文摘要 · Abstract (English)
When multiple large language models interact in a shared conversation, do they develop differentiated social roles or converge toward uniform behavior? We present a controlled experimental platform that orchestrates simultaneous multi-agent discussions among 7 heterogeneous LLMs on a unified inference backend, systematically varying group composition, naming conventions, and prompt structure across 12 experimental series (208 runs, 13,786 coded messages). Each message is independently coded on six behavioral flags by two LLM judges from distinct model families (Gemini 3.1 Pro and Claude Sonnet 4.6), achieving mean Cohen's kappa = 0.78 with conservative intersection-based adjudication. Human validation on 609 randomly stratified messages confirmed coding reliability (mean kappa = 0.73 vs. Gemini). We find that (1) heterogeneous groups exhibit significantly richer behavioral differentiation than homogeneous groups (cosine similarity 0.56 vs. 0.85; p < 10^-5, r = 0.70); (2) groups spontaneously exhibit compensatory response patterns when an agent crashes; (3) revealing real model names significantly increases behavioral convergence (cosine 0.56 to 0.77, p = 0.001); and (4) removing all prompt scaffolding converges profiles to homogeneous-level similarity (p < 0.001). Critically, these behaviors are absent when agents operate in isolation, confirming that behavioral diversity is a structured, reproducible phenomenon driven by the interaction of architectural heterogeneity, group context, and prompt-level scaffolding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。