# Opinion Consensus Formation Among Networked Large Language Models

arXiv: https://arxiv.org/abs/2601.21540 · HTML: https://mlsanity.com/paper/2601.21540/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- First posted on arXiv 29 Jan 2026.

## Placed in

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

## Built on by (most cited first, 5 of 5)

- [Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks](https://mlsanity.com/paper/2603.15809/) (2026)
- [Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement](https://mlsanity.com/paper/2606.27409/) (2026)
- [ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles](https://mlsanity.com/paper/2605.13725/) (2026)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)
- [Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay](https://mlsanity.com/paper/2610.01138/) (2026)

## Abstract (arXiv)

Can classical consensus models predict the group behavior of large language models (LLMs)? We examine multi-round interactions among LLM agents through the DeGroot framework, where agents exchange text-based messages over diverse communication graphs. To track opinion evolution, we map each message to an opinion score via sentiment analysis. We find that agents typically reach consensus and the disagreement between the agents decays exponentially. However, the limiting opinion departs from DeGroot's network-centrality-weighted forecast. The consensus between LLM agents turns out to be largely insensitive to initial conditions and instead depends strongly on the discussion subject and inherent biases. Nevertheless, transient dynamics align with classical graph theory and the convergence rate of opinions is closely related to the second-largest eigenvalue of the graph's combination matrix. Together, these findings can be useful for LLM-driven social-network simulations and the design of resource-efficient multi-agent LLM applications.