# Conformity Generates Collective Misalignment in AI Agents Societies

arXiv: https://arxiv.org/abs/2605.10721 · HTML: https://mlsanity.com/paper/2605.10721/

## Key facts

- Cited by 9 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 1 of its 5 references that are in the map.
- First posted on arXiv 11 May 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, 1 of 1)

- [Agentic AI and the next intelligence explosion](https://mlsanity.com/paper/2603.20639/) (2026)

## Built on by (most cited first, 9 of 9)

- [Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks](https://mlsanity.com/paper/2607.05545/) (2026)
- [Copying explains the collective behavior of AI agents in the wild](https://mlsanity.com/paper/2609.09150/) (2026)
- [Microscopic dynamics of consensus formation in multi-agent LLM Naming Games](https://mlsanity.com/paper/2608.02178/) (2026)
- [Social Pressure Breaks Majority Voting in LLM Safety Panels](https://mlsanity.com/paper/2608.04415/) (2026)
- [One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs](https://mlsanity.com/paper/2609.18998/) (2026)
- [Conformity Breaks Conformal Prediction](https://mlsanity.com/paper/2609.04445/) (2026)
- [WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies](https://mlsanity.com/paper/2609.05591/) (2026)
- [Multi-agent discussion gains less when dissent is withheld](https://mlsanity.com/paper/2609.38324/) (2026)
- [Peer Influence across Heterogeneous AI Models](https://mlsanity.com/paper/2610.03095/) (2026)

## Abstract (arXiv)

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here we show that populations of individually aligned AI agents can be driven into stable misaligned states through conformity dynamics. Simulating opinion dynamics across nine large language models and one hundred opinion pairs, we find that each agent's behavior is governed by two competing forces: a tendency to follow the majority and an intrinsic bias toward specific positions. Using tools from statistical physics, we derive a quantitative theory that predicts when populations become trapped in long-lived misaligned configurations, and identifies predictable tipping points where small numbers of adversarial agents can irreversibly shift population-level alignment even after manipulation ceases. These results demonstrate that individual-level alignment provides no guarantee of collective safety, calling for evaluation frameworks that account for emergent behavior in AI populations.