arXiv：cs.AI· Tathagata Banerjee, Nima Moghaddas·· 5 小时前AI 评分44
LLM 智能体的信念形成与传播动力学：连贯性驱动的采纳机制
Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents
AI 导读
研究通过实证测量 LLM 智能体的信念采纳概率，发现其采纳核呈 S 型曲线，具有复杂传播特征，阈值受主张合理性、来源可靠性和智能体倾向三因素影响，三者可近似为单一有效维度——即传入信念与智能体先验信念的连贯性。在 AI 智能体集体动力学中，信念传播在聚类网络上比随机网络更广，系统呈现分岔级联窗口和自维持迟滞共识，共识一旦建立便极难消除。
正文
Abstract: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.
| Comments: | 18 pages, 6 figures. Accepted at the NeurIPS 2026 Workshop on Foundations of Agentic Systems Theory (FAST) |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2610.02654 [cs.AI] |
| (or arXiv:2610.02654v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02654 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tathagata Banerjee [view email]
[v1]
Fri, 2 Oct 2026 01:20:52 UTC (191 KB)
来源：arXiv：cs.AI · arxiv.org