mlsanityData to 7 Oct 2026

MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations

arXiv 2504.07830 ↗First posted 10 Apr 2025cs.CL cs.AI cs.SIcited by 26

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

We present a novel, open-source social network simulation framework, MOSAIC, where generative language agents predict user behaviors such as liking, sharing, and flagging content. This simulation combines LLM agents with a directed social graph to analyze emergent deception behaviors and gain a better understanding of how users determine the veracity of online social content. By constructing user representations from diverse fine-grained personas, our system enables multi-agent simulations that model content dissemination and engagement dynamics at scale. Within this framework, we evaluate three different content moderation strategies with simulated misinformation dissemination, and we find that they not only mitigate the spread of non-factual content but also increase user engagement. In addition, we analyze the trajectories of popular content in our simulations, and explore whether simulation agents' articulated reasoning for their social interactions truly aligns with their collective engagement patterns. We open-source our simulation software to encourage further research within AI and social sciences.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 24 of its 95 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

24 of 95 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Large Language Model Driven Agents for Simulating Echo Chamber Formation25 Feb
  2. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society12 Feb
  3. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals15 Nov
  4. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 20

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  4. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  5. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  6. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  7. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 89
  8. 2024Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligencecited by 80
  9. 2023Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledgecited by 32
  10. 2024LLMs generate structurally realistic social networks but overestimate political homophilycited by 31
  11. 2022Crowdsourced Fact-Checking at Twitter: How Does the Crowd Compare With Experts?cited by 16
  12. 2023Personalizing Content Moderation on Social Media: User Perspectives on Moderation Choices, Interface Design, and Laborcited by 16
8 more
  1. 2013Origins of power-law degree distribution in the heterogeneity of human activity in social networkscited by 9
  2. 2025Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generationcited by 8
  3. 2025Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithmscited by 5
  4. 2022On the Effect of Triadic Closure on Network Segregationcited by 3
  5. 2024Challenging the Machine: Contestability in Government AI Systemscited by 3
  6. 2014Aggregate Characterization of User Behavior in Twitter and Analysis of the Retweet Graphcited by 2
  7. 2020Anger makes fake news viral onlinecited by 2
  8. 2020Conspiracy vs science: A large-scale analysis of online discussion cascadescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 19.

26 papers.

Sort:

By area:

  1. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  2. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 12
  3. 2025Agentic Services Computingcited by 6
  4. 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Auditscited by 6
  5. 2026PM-Bench: Evaluating Prospective Memory in LLM Agentscited by 6
  6. 2025Computational Turing Test Reveals Systematic Differences Between Human and AI Languagecited by 5
  7. 2025Agent-based simulation of online social networks and disinformationcited by 3
  8. 2026How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?cited by 3
  9. 2025G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulationcited by 2
  10. 2026From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communitiescited by 2
  11. 2026Simulating Human Memory with Language Modelscited by 2
  12. 2025Synthia: Scalable Grounded Persona Generation from Social Media Datacited by 1
14 more
  1. 2026Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online Newscited by 1
  2. 2026Ahead of the Spread: Agent-Driven Virtual Propagation for Early Fake News Detectioncited by 0
  3. 2026Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussionscited by 0
  4. 2026An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detectioncited by 0
  5. 2026ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profilescited by 0
  6. 2026You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformationcited by 0
  7. 2026Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision Policiescited by 0
  8. 2026MiroBench: Benchmarking Realism in Agentic Simulation of Real-world Discussionscited by 0
  9. 2026Automatic Hard Example Synthesis with Multi-Level Agentic Data Curationcited by 0
  10. 2026Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systemscited by 0
  11. 2026Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sourcescited by 0
  12. 2026Belief Cascades Drive Persuasion in LLM Agent Networkscited by 0
  13. 2026LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystemscited by 0
  14. 2026LLMs for Social Network Modeling: From Network Generation to Dynamic Processescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism
  2. 2024Agent-Based Modelling Meets Generative AI in Social Network Simulations
  3. 2025Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
  4. 2024Large Language Model-driven Multi-Agent Simulation for News Diffusion Under Different Network Structures
  5. 2026Behavioral Determinants of Deployed AI Agents in Social Networks: A Multi-Factor Study of Personality, Model, and Guardrail Specification
  6. 2026From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media
  7. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
  8. 2026Social Simulacra in the Wild: AI Agent Communities on Moltbook