Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias
Abstract
Language-model agents now interact in groups, but evaluations that probe memorised stereotype content or use models to simulate people leave this social behaviour unmeasured. We adapt the minimal-group paradigm---social psychology's classic test of intergroup bias---into a controlled probe: an agent distributes points among anonymous peers bearing only an arbitrary group label. Across four reasoning models, mere categorisation into meaningless groups elicited in-group favouritism that vanished under a group-blind control and was concentrated in the numerical minority: minority deciders over-allocated to their own group relative to their numbers, majority deciders allocated close to proportionally, and the asymmetry closed at equal group sizes. Disabling reasoning in one model did not remove the disposition---if anything it grew---but nearly erased the minority-majority asymmetry, implicating deliberation in where bias concentrates rather than whether it appears. These open-weight reasoning models reproduce the behavioural signature of human intergroup discrimination, independent of stereotype content, and social psychology's theories and methods offer a paradigm for measuring and governing AI's social behaviour.
Related
- Can Coding Agents Reproduce Findings in Computational Materials Science?
- Social influence aggregation on Weibo: psychological process expectations and meso-level cascade regimes in media psychology
- Quantum Encoding Agents: A Natural Language Interface for Data Embedding Strategy Selection in Quantum Machine Learning
- Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents
- Value-level data provenance in an electronic laboratory notebook used by humans and language-model agents: An experience report
BibTeX
@misc{lee2026toward,
title = {{Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias}},
author = {Messi H. J. Lee},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00009},
eprint = {2609.00009},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00009},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias
AU - Messi H. J. Lee
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00009
UR - https://arxiv.org/abs/2609.00009
AB - Language-model agents now interact in groups, but evaluations that probe memorised stereotype content or use models to simulate people leave this social behaviour unmeasured. We adapt the minimal-group paradigm---social psychology's classic test of intergroup bias---into a controlled probe: an agent distributes points among anonymous peers bearing only an arbitrary group label. Across four reasoning models, mere categorisation into meaningless groups elicited in-group favouritism that vanished under a group-blind control and was concentrated in the numerical minority: minority deciders over-allocated to their own group relative to their numbers, majority deciders allocated close to proportionally, and the asymmetry closed at equal group sizes. Disabling reasoning in one model did not remove the disposition---if anything it grew---but nearly erased the minority-majority asymmetry, implicating deliberation in where bias concentrates rather than whether it appears. These open-weight reasoning models reproduce the behavioural signature of human intergroup discrimination, independent of stereotype content, and social psychology's theories and methods offer a paradigm for measuring and governing AI's social behaviour.
ER -