City Research Online

Abstract

Social conventions are the backbone of social coordination, shaping how individuals form a group. As growing populations of artificial intelligence (AI) agents communicate through natural language, a fundamental question is whether they can bootstrap the foundations of a society. Here, we present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents. We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually. Last, we examine how committed minority groups of adversarial LLM agents can drive social change by imposing alternative social conventions on the larger population. Our results show that AI systems can autonomously develop social conventions without explicit programming and have implications for designing AI systems that align, and remain aligned, with human values and societal goals.

Publication Type:	Article
Additional Information:	Copyright © 2025 the Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. no claim to original U.S. Government Works. distributed under a creative commons Attribution noncommercial license 4.0 (cc BY- nc).
Subjects:	H Social Sciences > H Social Sciences (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology School of Science & Technology > Mathematics
SWORD Depositor:	Symplectic Administrator

Export

Downloads