AI智能体重塑人类群体中的共识形成

中文摘要 AI 辅助

随着大语言模型（LLM）智能体从工具转变为人类群体的参与者，它们日益增长的存在如何重塑共识形成，成为集体行为领域的一个基本问题。本研究在协作描述游戏中探究了混合人类-AI群体，该游戏中共享惯例通过多轮随机成对交流产生。通过改变LLM智能体的比例，我们识别出三种不同的共识形成 regime：低智能体比例有利于人类主导的共识，中等比例会破坏收敛，高比例则恢复强共识并使其转向智能体主导的惯例。关键的是，这些 regime 不仅在收敛强度上存在差异，还在所得共识的语义基础和交流形式上不同：人类主导的共识更具体、全面，且基于共享的现实世界类比；而智能体主导的共识更抽象、信息密度更低，且在几何上更碎片化。从机制上看，智能体的影响源于共同的语言先验，该先验将智能体置于表达空间中彼此靠近的位置，加上各轮之间相对稳定的表达选择；人类最初会抵制采用被视为AI的伙伴的表达，但逐渐屈服于从众压力。这些发现提供了证据，表明AI的组成可以塑造群体规范的出现、内容和感知合法性，使得智能体比例和透明度成为人机系统的重要设计变量。

英文摘要

As large language model (LLM) agents shift from tools to participants in human groups, a fundamental question for collective behavior is how their growing presence reshapes consensus formation. Here we study mixed human-AI groups in a collaborative description game, in which shared conventions emerge through repeated rounds of random pairwise communication. Varying the proportions of LLM agents, we identify three distinct regimes of consensus formation: low agent proportions facilitate human-led consensus, intermediate proportions disrupt convergence, and high proportions restore strong consensus while shifting it toward agent-led conventions. Crucially, these regimes differ not only in the strength of convergence, but also in the semantic grounding and communicative form of the resulting consensus: human-led consensus is more concrete, holistic, and grounded in shared real-world analogies, whereas agent-led consensus is more abstract, less information-dense, and more geometrically segmented. Mechanistically, agent influence arises from a shared linguistic prior that places agents near one another in the expression space, combined with relatively stable expression choices across rounds; humans initially resist adopting expressions from partners perceived as AI but gradually yield to conformity pressure. These findings provide evidence that AI composition can shape the emergence, content, and perceived legitimacy of group norms, making agent proportion and transparency important design variables for human-AI systems.

发表机构

• Network Science Institute, Northeastern University（东北大学网络科学研究所）
• Tsinghua University（清华大学）
• Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）
• Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

机构由 AI 辅助整理，请以论文原文为准。