发表机构
Takeda Pharmaceuticals; Northeastern University（武田制药; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究实证测量LLM智能体的信念采纳，发现其呈S形复杂传染特征，阈值受主张合理性、来源可靠性和智能体倾向影响，可归约为一致性维度，且在聚类网络上传播更广，共识难以消除。
AI 中文摘要
社会传染模型通常假设个体如何采纳信念，并据此推导出群体行为。我们则通过实证测量语言模型智能体中的信念采纳，量化智能体在给定多少同伴认可某主张时采纳该主张的概率。我们发现这一采纳核函数呈S形，这是复杂传染的特征，其阈值对三个来源敏感：主张的合理性、来源的可靠性以及智能体的倾向性。这三个维度可以很好地近似为一个单一有效维度，我们提出该维度可理解为传入信念与LLM智能体先前信念的一致性。此外，我们在AI智能体系统中的信念采纳集体动力学中观察到复杂传染的一个特征：在聚类网络上的传播比在随机网络上更广泛。这些系统还表现出分岔级联窗口和自维持的滞后共识，这导致共识的消除远比建立困难。
英文摘要
Models of social contagion usually assume how individuals adopt beliefs and derive population behavior from it. We instead empirically measure belief adoption in language model agents, quantifying the probability an agent adopts a claim given how many peers endorse it. We find this adoption kernel to be sigmoid, a characteristic of complex contagion, with a threshold that is sensitive to three sources: the claim's plausibility, the source's reliability, and the agent's disposition. These three dimensions are well approximated by a single effective dimension which we propose can be understood as the coherence of the incoming belief with the LLM agent's prior beliefs. Further, we observe a characteristic of complex contagion in the collective dynamics of belief adoption in a system of AI agents: further spread on clustered than random networks. These systems also exhibit a bifurcating cascade window, and self-sustaining hysteretic consensus which lead to consensus being far harder to remove than to establish.
Comments18 pages, 6 figures. Accepted at the NeurIPS 2026 Workshop on Foundations of Agentic Systems Theory (FAST)
