# Network Formation and Dynamics Among Multi-LLMs

arXiv: https://arxiv.org/abs/2402.10659 · HTML: https://mlsanity.com/paper/2402.10659/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 23 of its 87 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Community Detection and Stochastic Block Models](https://mlsanity.com/paper/1703.10146/) (2017)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Let Your Graph Do the Talking: Encoding Structured Data for LLMs](https://mlsanity.com/paper/2402.05862/) (2024)
- [Who is GPT-3? An Exploration of Personality, Values and Demographics](https://mlsanity.com/paper/2209.14338/) (2022)
- [Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks](https://mlsanity.com/paper/2306.07899/) (2023)
- [LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding](https://mlsanity.com/paper/2306.14924/) (2023)
- [GraphWorld: Fake Graphs Bring Real Insights for GNNs](https://mlsanity.com/paper/2203.00112/) (2022)
- [Do LLM Agents Exhibit Social Behavior?](https://mlsanity.com/paper/2312.15198/) (2023)
- [Emergence of Scale-Free Networks in Social Interactions among Large Language Models](https://mlsanity.com/paper/2312.06619/) (2023)
- [Choosing to Grow a Graph: Modeling Network Formation as Discrete Choice](https://mlsanity.com/paper/1811.05008/) (2018)
- [Leveraging Large Language Models for Collective Decision-Making](https://mlsanity.com/paper/2311.04928/) (2023)
- [Interpretable Stochastic Block Influence Model: measuring social influence among homophilous communities](https://mlsanity.com/paper/2006.01028/) (2020)
- [Investigating and Modeling the Dynamics of Long Ties](https://mlsanity.com/paper/2109.10523/) (2021)

## Built on by (most cited first, 29 of 29)

- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents](https://mlsanity.com/paper/2410.20746/) (2024)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)
- [Emergence of polarization in networks of large language model agents](https://mlsanity.com/paper/2501.05171/) (2025)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs](https://mlsanity.com/paper/2601.11369/) (2026)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [Tracking the perspectives of interacting language models](https://mlsanity.com/paper/2406.11938/) (2024)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [Social Opinions Prediction Utilizes Fusing Dynamics Equation with LLM-based Agents](https://mlsanity.com/paper/2409.08717/) (2024)
- [LLM-Based Multi-Agent Systems are Scalable Graph Generative Models](https://mlsanity.com/paper/2410.09824/) (2024)
- [LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis](https://mlsanity.com/paper/2503.22718/) (2025)
- [Don't Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism](https://mlsanity.com/paper/2506.21974/) (2025)
- [Simulating Influence Dynamics with LLM Agents](https://mlsanity.com/paper/2503.08709/) (2025)
- [Detecting Perspective Shifts in Multi-agent Systems](https://mlsanity.com/paper/2512.05013/) (2025)
- [Agent-based simulation of online social networks and disinformation](https://mlsanity.com/paper/2512.22082/) (2025)
- [Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks](https://mlsanity.com/paper/2512.18094/) (2025)
- [An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents](https://mlsanity.com/paper/2602.03775/) (2026)
- [Social Networks of LLM Agents](https://mlsanity.com/paper/2607.03695/) (2026)
- [Copying explains the collective behavior of AI agents in the wild](https://mlsanity.com/paper/2609.09150/) (2026)
- [Modeling Hypergraph Using Large Language Models](https://mlsanity.com/paper/2510.11728/) (2025)
- [Large language models for spreading dynamics in complex systems](https://mlsanity.com/paper/2602.08085/) (2026)
- [Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing Synthesis](https://mlsanity.com/paper/2605.12507/) (2026)
- [Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game](https://mlsanity.com/paper/2606.28456/) (2026)
- [Collaborative Spatial Learning with Multi-LLM Agents in Networked Social Experiments](https://mlsanity.com/paper/2607.14574/) (2026)
- [Insurance as AI Risk Infrastructure: A Generative-Agent Simulation of AI Adoption](https://mlsanity.com/paper/2608.15181/) (2026)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)
- [From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations](https://mlsanity.com/paper/2610.16498/) (2026)

## Abstract (arXiv)

Social networks profoundly influence how humans form opinions, exchange information, and organize collectively. As large language models (LLMs) are increasingly embedded into social and professional environments, it is critical to understand whether their interactions approximate human-like network dynamics. We develop a framework to study the network formation behaviors of multiple LLM agents and benchmark them against human decisions. Across synthetic and real-world settings, including friendship, telecommunication, and employment networks, we find that LLMs consistently reproduce fundamental micro-level principles such as preferential attachment, triadic closure, and homophily, as well as macro-level properties including community structure and small-world effects. Importantly, the relative emphasis of these principles adapts to context: for example, LLMs favor homophily in friendship networks but heterophily in organizational settings, mirroring patterns of social mobility. A controlled human-subject survey confirms strong alignment between LLMs and human participants in link-formation decisions. These results establish that LLMs can serve as powerful tools for social simulation and synthetic data generation, while also raising critical questions about bias, fairness, and the design of AI systems that participate in human networks.