Paper
Learning dynamics from online-offline systems of LLM agents
Authors
Moyi Tian, George Mohler, P. Jeffrey Brantingham, Nancy Rodríguez
Abstract
Online information is increasingly linked to real-world instability, especially as automated accounts and LLM-based agents help spread and amplify news. In this work, we study how information spreads on networks of Large Language Models (LLMs) using mathematical models. We investigate how different types of offline events, along with the "personalities" assigned to the LLMs, affect the network dynamics of online information spread of the events among the LLMs. We introduce two models: 1) a stochastic agent-based network model and 2) a system of differential equations arising from a mean-field approximation to the agent-based model. We fit these models to simulations of the spread of armed-conflict news on social media, using LLM agents each with one of 32 personality trait profiles on k-regular random networks. Our results indicate that, despite the complexity of the news events, personalities, and LLM behaviors, the overall dynamics of the system are well described by a Susceptible-Infected (SI) type model with two transmission rates.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.23437v1</id>\n <title>Learning dynamics from online-offline systems of LLM agents</title>\n <updated>2026-02-26T19:02:00Z</updated>\n <link href='https://arxiv.org/abs/2602.23437v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.23437v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Online information is increasingly linked to real-world instability, especially as automated accounts and LLM-based agents help spread and amplify news. In this work, we study how information spreads on networks of Large Language Models (LLMs) using mathematical models. We investigate how different types of offline events, along with the \"personalities\" assigned to the LLMs, affect the network dynamics of online information spread of the events among the LLMs. We introduce two models: 1) a stochastic agent-based network model and 2) a system of differential equations arising from a mean-field approximation to the agent-based model. We fit these models to simulations of the spread of armed-conflict news on social media, using LLM agents each with one of 32 personality trait profiles on k-regular random networks. Our results indicate that, despite the complexity of the news events, personalities, and LLM behaviors, the overall dynamics of the system are well described by a Susceptible-Infected (SI) type model with two transmission rates.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.SI'/>\n <category scheme='http://arxiv.org/schemas/atom' term='math.DS'/>\n <category scheme='http://arxiv.org/schemas/atom' term='nlin.AO'/>\n <category scheme='http://arxiv.org/schemas/atom' term='physics.soc-ph'/>\n <published>2026-02-26T19:02:00Z</published>\n <arxiv:comment>16 pages, 16 figures, 2 tables</arxiv:comment>\n <arxiv:primary_category term='cs.SI'/>\n <author>\n <name>Moyi Tian</name>\n </author>\n <author>\n <name>George Mohler</name>\n </author>\n <author>\n <name>P. Jeffrey Brantingham</name>\n </author>\n <author>\n <name>Nancy Rodríguez</name>\n </author>\n </entry>"
}