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

arXiv: https://arxiv.org/abs/2610.02654 · HTML: https://mlsanity.com/paper/2610.02654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 17 of 17)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs](https://mlsanity.com/paper/2510.19107/) (2025)
- [Delving into: the quantification of Ai-generated content on the internet (synthetic data)](https://mlsanity.com/paper/2504.08755/) (2025)
- [Emergence of simple and complex contagion dynamics from weighted belief networks](https://mlsanity.com/paper/2301.02368/) (2023)
- [Opinion Dynamics with Confirmation Bias](https://mlsanity.com/paper/1411.4328/) (2014)
- [Revealing complexities when adult readers engage in the credibility evaluation of social media posts](https://mlsanity.com/paper/2303.09656/) (2023)
- [Diffusion of complex contagions is shaped by a trade-off between reach and reinforcement](https://mlsanity.com/paper/2411.07907/) (2024)
- [You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation](https://mlsanity.com/paper/2605.17353/) (2026)
- [Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models](https://mlsanity.com/paper/2607.27512/) (2026)

## Abstract (arXiv)

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.