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

arXiv: https://arxiv.org/abs/2504.07830 · HTML: https://mlsanity.com/paper/2504.07830/

## Key facts

- Cited by 27 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.
- Builds on 24 of its 95 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [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)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence](https://mlsanity.com/paper/2407.07061/) (2024)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)
- [Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge](https://mlsanity.com/paper/2311.09731/) (2023)
- [Personalizing Content Moderation on Social Media: User Perspectives on Moderation Choices, Interface Design, and Labor](https://mlsanity.com/paper/2305.10374/) (2023)
- [Crowdsourced Fact-Checking at Twitter: How Does the Crowd Compare With Experts?](https://mlsanity.com/paper/2208.09214/) (2022)
- [Origins of power-law degree distribution in the heterogeneity of human activity in social networks](https://mlsanity.com/paper/1304.4523/) (2013)
- [Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generation](https://mlsanity.com/paper/2502.12073/) (2025)
- [Large Language Model Driven Agents for Simulating Echo Chamber Formation](https://mlsanity.com/paper/2502.18138/) (2025)
- [Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms](https://mlsanity.com/paper/2502.19193/) (2025)
- [On the Effect of Triadic Closure on Network Segregation](https://mlsanity.com/paper/2205.13658/) (2022)
- [Challenging the Machine: Contestability in Government AI Systems](https://mlsanity.com/paper/2406.10430/) (2024)
- [Aggregate Characterization of User Behavior in Twitter and Analysis of the Retweet Graph](https://mlsanity.com/paper/1402.2671/) (2014)
- [Anger makes fake news viral online](https://mlsanity.com/paper/2004.10399/) (2020)
- [Conspiracy vs science: A large-scale analysis of online discussion cascades](https://mlsanity.com/paper/2006.00765/) (2020)

## Built on by (most cited first, 27 of 27)

- [WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance](https://mlsanity.com/paper/2511.12997/) (2025)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits](https://mlsanity.com/paper/2605.18890/) (2026)
- [PM-Bench: Evaluating Prospective Memory in LLM Agents](https://mlsanity.com/paper/2607.12385/) (2026)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [Computational Turing Test Reveals Systematic Differences Between Human and AI Language](https://mlsanity.com/paper/2511.04195/) (2025)
- [Agent-based simulation of online social networks and disinformation](https://mlsanity.com/paper/2512.22082/) (2025)
- [How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?](https://mlsanity.com/paper/2602.18464/) (2026)
- [G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation](https://mlsanity.com/paper/2508.05709/) (2025)
- [From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities](https://mlsanity.com/paper/2604.03920/) (2026)
- [Simulating Human Memory with Language Models](https://mlsanity.com/paper/2605.25680/) (2026)
- [Synthia: Scalable Grounded Persona Generation from Social Media Data](https://mlsanity.com/paper/2507.14922/) (2025)
- [You Can't Fool Us: Understanding the Resilience of LLM-driven Agent Communities to Misinformation](https://mlsanity.com/paper/2605.17353/) (2026)
- [Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News](https://mlsanity.com/paper/2605.28598/) (2026)
- [Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2608.03239/) (2026)
- [Ahead of the Spread: Agent-Driven Virtual Propagation for Early Fake News Detection](https://mlsanity.com/paper/2601.02750/) (2026)
- [Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions](https://mlsanity.com/paper/2603.21194/) (2026)
- [An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection](https://mlsanity.com/paper/2605.02259/) (2026)
- [ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles](https://mlsanity.com/paper/2605.13725/) (2026)
- [Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision Policies](https://mlsanity.com/paper/2606.12369/) (2026)
- [MiroBench: Benchmarking Realism in Agentic Simulation of Real-world Discussions](https://mlsanity.com/paper/2606.14715/) (2026)
- [Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation](https://mlsanity.com/paper/2607.14256/) (2026)
- [Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources](https://mlsanity.com/paper/2608.20438/) (2026)
- [Belief Cascades Drive Persuasion in LLM Agent Networks](https://mlsanity.com/paper/2608.25152/) (2026)
- [LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems](https://mlsanity.com/paper/2608.26849/) (2026)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)
- [PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation](https://mlsanity.com/paper/2610.14570/) (2026)

## 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.