Opinion Dynamics and Social Influence

Latest papers

• Population Physics, Population Problems: Safety and Emergence in LLM Societies

  Adrian de Wynter · 30 September 2026

  The collective behaviour of large language model (LLM) societies is not the sum of their individual outputs. It yields statistically distinct, sometimes-unpredictable phenomena, for which the tools we use to study single agents may not scale. Due to recent incidents involving autonomous agentic syst…

• Local Predictability and Collective Fidelity in LLM-Agent Societies

  Igor Itkin · 30 September 2026

  Compact surrogates could reduce the cost of simulating large language model societies, but must reproduce collective behavior. We compare individual predictions and collective forecasts using 9,455 published trajectories and new experiments on opinion dynamics. Neighbor information improves individu…

• Group dynamics of engagement with AI topics on Bluesky

  Bradley Huynh, Moyi Tian, Nancy Rodr\'iguez · 30 September 2026

  Social media increasingly shapes everyday life, serving as both a central venue for discussion of major events and a space where online collective behavior can spill over into real-world activity, while artificial intelligence (AI) is likewise becoming increasingly influential across society. Unders…

• Learning Collective Dynamics with Differentiable Gaussian Representations

  Jianxiang Ma, Mingfu Zhang, Xiaocui Yang, Yichen Gao, Junzhao Huang, Yuesong Hou · 24 September 2026

  Collective responses depend on individual differences, contact opportunities, and accumulated experience. Learning their dynamics from aggregate counts requires connecting a population's response distribution to both current observations and future behavior. We introduce Differentiable Gaussian Dyna…

• Indirect tipping: a social attack surface in AI agent populations

  Ariel Flint, Luca Maria Aiello, Sara M. Constantino, Romualdo Pastor-Satorras, Andrea Baronchelli · 23 September 2026

  As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on collective equilibria that determine how agent populations process information, prioritize actions, and respond to uncertainty. Yet the same equilibria that ena…

• Opinion Leader Dynamics: How Sparse Attention Shapes Token Clustering

  Jingkun Liu, Yue Song · 22 September 2026

  Sparse attention reduces the quadratic cost of global self-attention while retaining strong empirical performance, but how its restricted interactions shape the evolution of token representations remains theoretically underexplored. Modeling tokens as particles on the unit sphere, we introduce opini…

• SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm

  Xinnong Zhang, Jiayu Lin, Jia Wang, Yixu Huang, Xinyi Mou, Yingqian Wu, Jingcong Liang, Shijun Lei, Jianing Shi, Guanying Li, Siyuan Wang, Hanjia Lyu, Zhenfei Yin, Yunlu Yin, Siming Chen, Yulan He, Jiebo Luo, Xuanjing Huang, Liyin Jin, Baohua Zhou, Hanqi Yan, Zhongyu Wei · 22 September 2026

  Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative agents have transformed it by acting as silicon samples that unite agent-based modeling with real behavioral data. Existing platforms verify collective behavior, align simulated …

• Inferring the microscopic mechanisms of opinion dynamics using a kinetic Ising model

  Ixandra Achitouv, David Chavalarias, Vincent Lahoche · 22 September 2026

  Kinetic Ising models are widely used to describe binary opinion dynamics, but their microscopic validity has rarely been tested empirically. Here, we infer the transition probabilities governing opinion updates from a year-long online social network and show that they are accurately described by an …

• Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents

  Hafsa Akbar, Daniel Platnick, Marjan Alirezaie, Hossein Rahnama · 21 September 2026

  LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified, and collective outcomes inherit the model's training prior. We introduce Bayesian Chronicle Agents (BCA), a minimal belief layer separating \emph{wh…

• Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks

  Omran Berjawi, Giuseppe Fenza, Rida Khatoun, Sherali Zeadally · 18 September 2026

  The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding political polarization, misinformation, and health responses. Current approaches focus on simplified mathematical models that ignore linguistic and con…

• Message capacity and claim wording set the transition points of collective truth-finding in language-model networks

  Makoto Fukushima · 18 September 2026

  Whether human or large language model (LLM), an agent in a discussion reads only a few of the others' contributions, bounded by cognition, context, or cost. LLM collectives can settle on a wrong consensus even when a majority starts out correct; we ask how far that reading bound alone decides the ou…

• Flag Game: A Toy Model for Mechanistic Swarm Interpretability

  Elizabeth Pavlova, Hidenori Tanaka · 17 September 2026

  Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs about the world, and mechanistic understanding is crucial for collective alignment. To this end, we introduce the Flag Game…

• Digital Persuasion: Understanding the Impact of Online Influencers on Public Opinion

  Omran Berjawi, Rida Khatoun, Giuseppe Fenza · 16 September 2026

  The studying of opinion dynamics and its propagation within social networks is crucial for addressing a wide range of challenges, including political polarization, public health, and marketing strategies. In this work, we study the problem of opinion dynamics by proposing a framework based on Friedk…

• An Evolutionary Computation Framework for Multi-Agent Q-Learning with Mean-Field Environmental Feedback

  Lichen Wang, Shijia Hua, Linjie Liu · 15 September 2026

  Multi-agent reinforcement learning in networked populations is governed by the interaction between individual adaptation, local encounters, and changing environmental conditions. To study this interaction, we formulate a coupled learning--environment model in which agents update stateless $Q$-values…

• Diverse Minds, Divided Networks? Personality Composition, Polarization, and Collective Intelligence in LLM-Based Social Simulations

  Raad Bin Tareaf · 14 September 2026

  Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two are rarely measured in the same system. It is therefore difficult to say whether a society's personality composition shapes both, or whether reducing…

• Modeling AI Overreliance as a Complex Adaptive System

  Ahana Biswas · 21 August 2026

  Whether AI assistance helps or harms a population depends less on the model's accuracy than on whether people rely on it appropriately trusting it when it is right and checking it when it is not. Yet reliance is usually studied one user at a time. We model it as a population process: agents repeated…

• GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities

  Haoran Bu, Zejian Chen, Litian Zhang, Xi Zhang · 19 August 2026

  LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may manipulate agents to induce group polarization. Existing methods manipulate agent prompts or construct echo chambers, both o…

• Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents

  Batu El, Jinhee Paeng, Fatih Dinc, Shiye Su, Mete Erdogan, Aneesh Pappu, Haotian Ye, Wanjia Zhao, Surya Ganguli, James Zou · 18 August 2026

  AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting th…

• "If It Looks Like a User": Measuring Real-Time Moderation Effects via Social Media Simulation

  Enrico Verdolotti, Gianluca Nogara, Luca Luceri, Silvia Giordano · 18 August 2026

  Agent-based social media simulators offer a controlled environment to study content moderation, yet their value hinges on how faithfully they reproduce real platform dynamics. We develop a calibrated extension of SimSoM, an agent-based model of information diffusion on social networks, grounded in a…

• Rethinking Learning-Based Influence Maximization: Simple Neural Surrogates and Native Discrete Search

  Yiqiao Liao, Parinaz Naghizadeh · 11 August 2026

  Existing learning-based influence maximization frameworks rely heavily on complex neural architectures and continuous optimization over seed representations. We challenge this paradigm with SIMBA, a diffusion-model-agnostic framework pairing a lightweight neural surrogate with direct discrete search…

• Imprecise Belief Fusion Improves Multi-agent Social Learning

  Zixuan Liu, Jonathan Lawry, Michael Crosscombe · 4 August 2026

  In social learning, agents learn not only from direct evidence but also through interactions with their peers. We investigate the role of imprecision in such interactions and ask whether it can improve the effectiveness of the collective learning process. To that end we propose a model of social lea…

• Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model

  Lynnette Hui Xian Ng, Kathleen M. Carley · 4 August 2026

  Social dynamics encode the process in which individual network and discourse interactions aggregate into collective influence, narrative dominance and coordinate behavior. This paper uses the the GhostField architecture, a hybrid LLM-Enabled Agent Based Network-Dynamic (LAND) model as a social simul…

• Artificially intelligent agents in the social and behavioral sciences: A history and outlook

  Petter Holme, Milena Tsvetkova · 21 July 2026

  We review the historical development and current trends of artificially intelligent agents (agentic AI) in the social and behavioral sciences: from the first programmable computers, and social simulations soon thereafter, to today's experiments with large language models. This overview emphasizes th…

• Sociocultural Influences on Opinion Formation: Word of Mouth Dynamics, Mass Media and Behavioural Development

  Elpida Tzafestas · 20 July 2026

  We study a society of agents belonging to a number of occupational or cultural groups that form opinions about others' situation in the same or different group. Opinions develop either by observation within own group or by directly interacting with members of other groups, therefore by word of mouth…

• From Global to Factor-Wise Expert Composition in Discrete Diffusion Models

  Haozhe Huang, Yudong Xu, Abhijoy Mandal, Al\'an Aspuru-Guzik · 14 July 2026

  Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data. Recent theoretical corrections introduce time-dependent mixing wei…