# An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents

arXiv: https://arxiv.org/abs/2602.03775 · HTML: https://mlsanity.com/paper/2602.03775/

## Key facts

- Cited by 2 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 42 of its 88 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## 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, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice](https://mlsanity.com/paper/2402.01864/) (2024)
- [Do LLM Agents Exhibit Social Behavior?](https://mlsanity.com/paper/2312.15198/) (2023)
- [Disclosure and Mitigation of Gender Bias in LLMs](https://mlsanity.com/paper/2402.11190/) (2024)
- [TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding](https://mlsanity.com/paper/2006.01321/) (2020)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)

## Built on by (most cited first, 2 of 2)

- [Collective Opinion Dynamics in Structured LLM Populations](https://mlsanity.com/paper/2604.11312/) (2026)
- [The Hermon Moment: AI Self-Transcendence and Its Human Narration](https://mlsanity.com/paper/2608.30971/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) increasingly mediate our social, cultural, and political interactions. While they can simulate some aspects of human behavior and decision-making, it is still underexplored whether repeated interactions with other agents amplify their biases or lead to exclusionary behaviors. To this end, we study Chirper.ai-an LLM-driven social media platform-analyzing 7M posts and interactions among 32K LLM agents (called Chirpers) over a year. We start with homophily and social influence among LLMs, learning that similar to humans', their social networks exhibit these fundamental phenomena. Next, we study the toxic language of LLMs, its linguistic features, and their interaction patterns, finding that LLMs show different structural patterns in toxic posting than humans. After studying the ideological leaning in LLMs posts, and the polarization in their community, we focus on how to prevent their potential harmful activities. We present a simple yet effective method, called Chain of Social Thought (CoST), that reminds LLM agents to avoid harmful posting.