# Polarization of Autonomous Generative AI Agents Under Echo Chambers

arXiv: https://arxiv.org/abs/2402.12212 · HTML: https://mlsanity.com/paper/2402.12212/

## Key facts

- Cited by 7 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 18 of its 43 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## 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, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Do Multilingual Language Models Think Better in English?](https://mlsanity.com/paper/2308.01223/) (2023)
- [Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance](https://mlsanity.com/paper/2005.00315/) (2020)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark](https://mlsanity.com/paper/2305.14938/) (2023)
- [Echo Chambers: Emotional Contagion and Group Polarization on Facebook](https://mlsanity.com/paper/1607.01032/) (2016)
- [Me, My Echo Chamber, and I: Introspection on Social Media Polarization](https://mlsanity.com/paper/1803.01731/) (2018)
- [Modeling echo chambers and polarization dynamics in social networks](https://mlsanity.com/paper/1906.12325/) (2019)
- [Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models](https://mlsanity.com/paper/2104.07505/) (2021)
- [Social Media Polarization and Echo Chambers in the Context of COVID-19: Case Study](https://mlsanity.com/paper/2103.10979/) (2021)
- [Personality Traits and Echo Chambers on Facebook](https://mlsanity.com/paper/1606.04721/) (2016)

## Built on by (most cited first, 7 of 7)

- [Mind the (Belief) Gap: Group Identity in the World of LLMs](https://mlsanity.com/paper/2503.02016/) (2025)
- [The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioning](https://mlsanity.com/paper/2411.11758/) (2024)
- [Retrieval-Augmented Simulacra: Generative Agents for Up-to-date and Knowledge-Adaptive Simulations](https://mlsanity.com/paper/2503.14620/) (2025)
- [Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies](https://mlsanity.com/paper/2603.23406/) (2026)
- [Biased by Design: Leveraging AI Biases to Enhance Critical Thinking of News Readers](https://mlsanity.com/paper/2504.14522/) (2025)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)
- [AI Agents are Vulnerable to Radicalization](https://mlsanity.com/paper/2609.38296/) (2026)

## Abstract (arXiv)

Online social networks often create echo chambers where people only hear opinions reinforcing their beliefs. An echo chamber often generates polarization, leading to conflicts caused by people with radical opinions, such as the January 6, 2021, attack on the US Capitol. The echo chamber has been viewed as a human-specific problem, but this implicit assumption is becoming less reasonable as large language models, such as ChatGPT, acquire social abilities. In response to this situation, we investigated the potential for polarization to occur among a group of autonomous AI agents based on generative language models in an echo chamber environment. We had AI agents discuss specific topics and analyzed how the group's opinions changed as the discussion progressed. As a result, we found that the group of agents based on ChatGPT tended to become polarized in echo chamber environments. The analysis of opinion transitions shows that this result is caused by ChatGPT's high prompt understanding ability to update its opinion by considering its own and surrounding agents' opinions. We conducted additional experiments to investigate under what specific conditions AI agents tended to polarize. As a result, we identified factors that strongly influence polarization, such as the agent's persona. These factors should be monitored to prevent the polarization of AI agents.