Ashery Ariel Flint, Aiello Luca Maria, Baronchelli Andrea
Department of Mathematics, City St George's, University of London, Northampton Square, London EC1V 0HB, UK.
Computer Science Department, IT University of Copenhagen, Rued Langgaards Vej 7, 2300 Copenhagen, Denmark.
Sci Adv. 2025 May 16;11(20):eadu9368. doi: 10.1126/sciadv.adu9368. Epub 2025 May 14.
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.
社会习俗是社会协调的支柱，塑造着个体如何形成群体。随着越来越多的人工智能（AI）智能体通过自然语言进行交流，一个基本问题是它们能否自行建立社会的基础。在此，我们展示了实验结果，这些结果证明了在大型语言模型（LLM）智能体的分散群体中普遍采用的社会习俗会自发出现。然后我们展示了在此过程中如何会出现强烈的集体偏见，即使智能体个体没有表现出偏见。最后，我们研究了对抗性LLM智能体组成的少数坚定群体如何通过将替代性社会习俗强加给更多群体来推动社会变革。我们的结果表明，人工智能系统无需明确编程就能自主形成社会习俗，这对于设计与人类价值观和社会目标相一致并保持一致的人工智能系统具有启示意义。
