# On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models

arXiv: https://arxiv.org/abs/2406.15492 · HTML: https://mlsanity.com/paper/2406.15492/

## Key facts

- Cited by 8 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 18 Jun 2024.

## 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, 8 of 8)

- [Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research](https://mlsanity.com/paper/2506.01839/) (2025)
- [Large Language Models can Achieve Social Balance](https://mlsanity.com/paper/2410.04054/) (2024)
- [Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks](https://mlsanity.com/paper/2510.06307/) (2025)
- [Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment](https://mlsanity.com/paper/2605.01147/) (2026)
- [When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies](https://mlsanity.com/paper/2606.22203/) (2026)
- [Collective Opinion Dynamics in Structured LLM Populations](https://mlsanity.com/paper/2604.11312/) (2026)
- [Where are the Humans? A Scoping Review of Fairness in Multi-agent AI Systems](https://mlsanity.com/paper/2604.15078/) (2026)
- [Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game](https://mlsanity.com/paper/2606.28456/) (2026)

## Abstract (arXiv)

We study the evolution of opinions inside a population of interacting large language models (LLMs). Every LLM needs to decide how much funding to allocate to an item with three initial possibilities: full, partial, or no funding. We identify biases that drive the exchange of opinions based on the LLM's tendency to find consensus with the other LLM's opinion, display caution when specifying funding, and consider ethical concerns in its opinion. We find these biases are affected by the perceived absence of compelling reasons for opinion change, the perceived willingness to engage in discussion, and the distribution of allocation values. Moreover, tensions among biases can lead to the survival of funding for items with negative connotations. We also find that the final distribution of full, partial, and no funding opinions is more diverse when an LLM freely forms its opinion after an interaction than when its opinion is a multiple-choice selection among the three allocation options. In the latter case, consensus is mostly attained. When agents are aware of past opinions, they seek to maintain consistency with them, changing the opinion dynamics. Our study is performed using Llama 3 and Mistral LLMs.