发表机构
Carnegie Mellon University（卡内基梅隆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过异构LLM模拟证明基础模型比人格更主导参与量，并随模型增多效应增强，强调异构组成对网络结果的关键作用。
AI 中文摘要
使用大型语言模型（LLM）的多智能体模拟通常以单一基础模型运行智能体网络。这忽略了模型间效应，而后者在真实部署中可能主导参与动态。为证明这一点，我们模拟了一个由多种不同基础模型驱动的异构社交网络，并表明智能体获得的参与量更多地取决于其基础模型而非其被分配的人格。当在混合中加入更多模型时，基础模型的吸引或排斥效应显著增强，这表明网络动态在规模上可能收敛于基础模型效应。为帮助解释这一效应，我们进行了一系列内容中介分析，展示了基础模型跨上下文的可预测性，以及模型词汇模式与参与最大化风格之间的关系。鉴于大规模多智能体交互的最新发展，这项工作强调了异构组成在驱动这些网络结果中的相关性。
英文摘要
Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model effects which may dominate engagement dynamics in real-world deployments. To show this, we simulate a heterogeneous social network powered by several different base models and show that the amount of engagement an agent receives depends more on its base model than on its assigned persona. The attraction or repulsion effects of a base model strengthen dramatically when more models are added in the mix, suggesting that networks dynamics may converge to base model effects at scale. To help explain this effect, we conduct a series of content-mediating analyses, showing the predictability of base models across contexts as well as the relationship between a model's lexical patterns and an engagement-maximizing style. In light of recent developments in mass multi-agent interaction, this work underscores the relevance of heterogeneous compositions in driving the outcomes of those networks
CommentsPresented as a Spotlight Paper at the Second Workshop on Social Simulation with LLMS, Third Conference on Language Modeling, 2026
