Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents

arXiv:2610.02654v1 Announce Type: new 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.

Related

• ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models
• How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation
• Bayesian Social Deduction with Graph-Informed Language Models
• A Study of Belief Revision Postulates in Multi-Agent Systems (Extended Version)
• GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities

Source: arXiv cs.AI | 2026-10-05