MIDSim: Simulating Multi-Channel Information Diffusion in Social Media with LLM-Powered Multi-Agent System

2026-06-11

AI Summary

This work addresses the limitations of existing information diffusion models, which predominantly focus on social tie-based propagation and fail to capture the multifaceted influence of platform recommendation algorithms and user behavioral complexity. To overcome this, the authors propose a large language model (LLM)-driven multi-agent simulation framework that integrates personalized LLM-powered agents into multi-channel diffusion modeling for the first time. The framework jointly incorporates social network topology and algorithmic recommendation mechanisms, leveraging real user profiles and multi-source social media data from Weibo, Xiaohongshu, and Twitter to generate dynamic diffusion trajectories. Experimental results demonstrate that the proposed approach successfully reproduces macroscopic diffusion patterns, produces diverse and contextually grounded comment content, and significantly outperforms existing baseline models in both realism and fine-grained behavioral fidelity.

Abstract

Information diffusion in social media shapes public opinion and collective behavior, making its modeling and simulation an important research problem. Existing studies have investigated information diffusion through epidemic-based, cascade-based, and point process models. However, they predominantly focus on diffusion through social links, overlooking other diffusion channels enabled by platform algorithms (e.g., recommender systems) and failing to capture user behavioral complexity. To address these limitations, we propose an LLM-powered multi-agent system for simulating multi-channel information diffusion, where large language models instantiate personalized user agents and the diffusion process jointly models social and algorithmic exposure streams. We further construct three real-world diffusion dataset spanning Sina Weibo, RedNote, and Twitter, containing diffusion records, user profiles, historical posts, and social relationships. Experimental results on real diffusion events show that our proposed framework realistically simulate macro diffusion phenomenon and generate diverse comment content, significantly outperforming baselines.

Problem

• information diffusion
• multi-channel diffusion
• social media
• algorithmic exposure
• user behavior complexity

Innovation

• LLM-powered multi-agent system
• multi-channel information diffusion
• algorithmic exposure
• social media simulation
• personalized user agents