Collective Opinion Dynamics in Structured LLM Populations

Erica Cau; Andrea Failla; Giulio Rossetti

cs.SIApr 13, 2026

Collective Opinion Dynamics in Structured LLM Populations

Authors: Erica Cau, Andrea Failla, Giulio Rossetti

Organizations: Department of Computer Science, University of Pisa · ISTI-CNR

Abstract

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.

Figures & tables

Figure 1 : Graphical schema of the LLM-OD framework. The LLM agents population is initialized as nodes in a network; each agent is an LLM instance with an initial opinion in the range [0, 6] (a). At each iteration, two neighbor agents are chosen and prompted to act as Opponent and Discussant (b). The Discussant is prompted to listen to the opinion of the Opponent around the discussion statement and may then accept, reject, or ignore such opinion (c) and update their current one accordingly by ±1 (d).

Panel of Figure 4 — Figure 4 : Opinion trends for Llama agents across different homophily levels for minority fraction $min=0.5$ (a), $min=0.3$ (b), and $min=0.1$ (c) Each panel shows the proportion of agents holding different opinion states over 100 iterations. All points of the opinion scale are mapped to the colors in the legend, from Strongly Disagree (dark red) to Strongly Agree (dark green).

Panel of Figure 5 — Figure 5 : Opinion trends for Gemma agents across different homophily levels for minority fraction $min=0.5(a)$ , $min=0.3$ (b), and $min=0.1$ (c) Each panel shows the proportion of agents holding different opinion states over 100 iterations. All points of the opinion scale are mapped to the colors in the legend, from Strongly Disagree (dark red) to Strongly Agree (dark green).

Panel of Figure 6 — Figure 6 : Opinion trends for Llama agents under neighborhood opinion awareness, across homophily levels, for minority fraction $min=0.5$ (a), $min=0.3$ (b), and $min=0.1$ (c) Each panel shows the proportion of agents holding different opinion states over 100 iterations. All points of the opinion scale are mapped to the colors in the legend, from Strongly Disagree (dark red) to Strongly Agree (dark green).

Panel of Figure 7 — Figure 7 : Opinion trends for Gemma agents under neighborhood opinion awareness, across homophily levels, for minority fraction $min=0.5$ (a), $min=0.3$ (b), and $min=0.1$ (c) Each panel shows the proportion of agents holding different opinion states over 100 iterations. All points of the opinion scale are mapped to the colors in the legend, from Strongly Disagree (dark red) to Strongly Agree (dark green).

Figure 8 : Conditional transition probabilities under balanced populations ( $\text{min}{=}0.5$ ) for Llama and Gemma. Each matrix reports $P(\text{disc}{\rightarrow}\text{opp}\mid o_{\text{disc}},o_{\text{opp}})$ , with the 7-point Likert scale collapsed into low- ( $0$ – $3$ ) and high-opinion ( $4$ – $6$ ) macrostates. Rows correspond to the Discussant ’s pre-interaction opinion class and columns to the Opponent ’s. Each matrix represent different homophily level $h\in\{0,\,0.25,\,0.5,\,0.75,\,1\}$ ; Only statistically significant entries ( $p{<}0.01$ , permutation test) are shown; non-significant cells are left blank.

Figure 9 : Facet plots of statistically significant opinion shifts for Llama agents under different neighborhood conditions. Each panel reports $P\bigl(disc\rightarrow opp\mid o_{disc},o_{opp},c\bigr)$ , where $c\in\{\text{misaligned},\text{mixed},\text{aligned}\}$ denotes the Discussant ’s local neighborhood relative to the direction of the potential opinion shift. Rows correspond to aligned, misaligned, and mixed neighborhoods, while columns vary the homophily level $h$ . Only statistically significant transitions are shown.

Figure 10 : Facet plots of statistically significant opinion shifts for Gemma agents under different neighborhood conditions. Each panel reports $P\bigl(disc\rightarrow opp\mid o_{disc},o_{opp},c\bigr)$ , where $c\in\{\text{aligned},\text{misaligned},\text{mixed}\}$ denotes the Discussant ’s local neighborhood relative to the direction of the potential opinion shift. Rows correspond to aligned, misaligned, and mixed neighborhoods, while columns vary the homophily level $h$ . Only statistically significant transitions are shown.

Explore similar work

Characterizing Opinion Evolution of Networked LLMs
Jun 5, 2026Caleb Probine, Yigit Ege Bayiz, Filippos Fotiadis +3Large Language Model Decisions Social Dynamics
The University of Texas at Austin
Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric
Sep 16, 2026Omran Berjawi, Giuseppe Fenza, Rida KhatounMulti-Agent Large Language Model Systems Multi-Agent Communication
Institut Polytechnique de Paris, Télécom Paris, Palaiseau, France · University of Salerno, Fisciano, Italy
Social Networks of LLM Agents
Jul 4, 2026Kaixuan Liu, Guojun Xiong, Weinan Zhang +1Large Language Model Agents Social Media
Department of Computer Science Emory University Atlanta, GA 30322 · School of Computer Science Shanghai Jiao Tong University Shanghai, China

Jun 5, 2026, cs.MAJ/K move · Enter open · S save

Characterizing Opinion Evolution of Networked LLMs

Caleb Probine, Yigit Ege Bayiz, Filippos Fotiadis, Samuel Li+2

The University of Texas at Austin

Large Language Model Decisions Social Dynamics Efficient Large Language Model Evolutionary Optimization Methods

Open paper AskPDF arXiv

Large language models (LLMs) increasingly interact with one another in multi-agent systems, from simulations of human discourse to influence operations and fully LLM-driven social platforms. These interactions give rise to new regimes of opinion propagation that are not yet well understood. We investigate whether classical opinion dynamics models, which have long been used to explain how interactions shape collective beliefs in human societies, can capture the behavior of LLM networks. We find that, while naive averaging-style models fail to track LLMs' opinion dynamics, simple modifications yield substantial gains in modeling fidelity. In particular, bias, an innate opinion toward which agents regress, emerges as a significant driver of LLM opinion dynamics, with its inclusion reducing cumulative estimated mean opinion error by up to 88%. We additionally find that these conclusions generalize across model families, discussion topics, and networks.

Abstract

Explore similar work

Characterizing Opinion Evolution of Networked LLMs

Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric

Social Networks of LLM Agents