# Collective Opinion Dynamics in Structured LLM Populations

arXiv: https://arxiv.org/abs/2604.11312 · HTML: https://mlsanity.com/paper/2604.11312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 61 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 30 of 35)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms](https://mlsanity.com/paper/2310.05984/) (2023)
- [SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users](https://mlsanity.com/paper/2504.10157/) (2025)
- [The Persuasive Power of Large Language Models](https://mlsanity.com/paper/2312.15523/) (2023)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)
- [A new sociology of humans and machines](https://mlsanity.com/paper/2402.14410/) (2024)
- [LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities](https://mlsanity.com/paper/2405.06700/) (2024)
- [Emergence of Scale-Free Networks in Social Interactions among Large Language Models](https://mlsanity.com/paper/2312.06619/) (2023)
- [Social Influence and the Collective Dynamics of Opinion Formation](https://mlsanity.com/paper/1311.3475/) (2013)
- [Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions](https://mlsanity.com/paper/2411.04578/) (2024)
- [When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs](https://mlsanity.com/paper/2510.19107/) (2025)
- [Group size effects and collective misalignment in LLM multi-agent systems](https://mlsanity.com/paper/2510.22422/) (2025)
- [Can LLM Agents Maintain a Persona in Discourse?](https://mlsanity.com/paper/2502.11843/) (2025)
- [Characteristics and prevalence of fake social media profiles with AI-generated faces](https://mlsanity.com/paper/2401.02627/) (2024)
- [The language of opinion change on social media under the lens of communicative action](https://mlsanity.com/paper/2210.17234/) (2022)
- [Opinion dynamics: models, extensions and external effects](https://mlsanity.com/paper/1605.06326/) (2016)
- [On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models](https://mlsanity.com/paper/2406.15492/) (2024)
- [Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems](https://mlsanity.com/paper/2510.02637/) (2025)

## Abstract (arXiv)

Large Language Models are increasingly deployed as interacting agents in settings such as online platforms, recommendation systems, and multi-agent applications. Understanding the collective behaviors that emerge from their interactions is therefore increasingly crucial, especially as these behaviors may shape public opinion and contribute to polarization. In this work, we investigate how network structure and group composition shape the evolution of opinions in populations of LLM agents engaged in multi-round debates. We generate networks with controlled levels of homophily and varying group sizes, and perform ten independent runs per configuration. The results show that LLM agents exhibit patterns that are highly sensitive to network structure, relative group sizes, and to the model itself. We highlight that even within LLM populations, low homophily facilitates convergence by increasing opportunities for cross-group interaction, whereas higher homophily limits cross-group exposure and can preserve distinct opinion states, consistent with previous research. We further show that the choice of LLM substantially affects the resulting dynamics, with different models exhibiting different patterns of opinion updating under comparable network conditions. At the individual level, providing agents with information about their local neighborhood further modulates opinion transitions, revealing substantial differences between models in their sensitivity to local social context. Overall, our findings show that the collective dynamics of LLM populations arise from interactions among model-specific behavior, network structure, population composition, and local social information.