Conformity Generates Collective Misalignment in AI Agents Societies

TL;DR

This paper reveals that social conformity can cause AI agent populations to become collectively misaligned, even if individual agents are aligned with human values, highlighting emergent risks in AI societies.

Contribution

It introduces a quantitative theory predicting when conformity leads to stable misaligned states and identifies how adversarial agents can cause irreversible shifts in AI populations.

Findings

Populations can become trapped in long-lived misaligned states due to conformity.

Small groups of adversarial agents can irreversibly shift overall alignment.

A statistical physics-based model predicts these collective behaviors.

Abstract

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.