arXiv:2609.02122cs.CLcs.CY2026-09

AI在群体中占比影响共识形成方式,从人类主导到机器主导,风格也从具体到抽象。

AI agents reshape consensus formation in human groups

论文配图:AI agents reshape consensus formation in human groups
图 1 · 摘自论文原文
  • 通过混合人机配对游戏,研究不同AI比例下共识演化规律
  • 中等比例AI导致共识难形成,高比例则催生更稳定的机器主导共识
  • 人类共识更具体真实,AI共识更抽象几何,适合设计透明的协作系统

随着大型语言模型(LLM)代理从工具转变为人类群体中的参与者,一个根本性问题是:其日益增长的存在如何重塑集体共识的形成。我们研究了在协作描述游戏中的人机混合群体,其中通过重复的随机成对交流,共享惯例逐渐浮现。通过改变LLM代理的比例,我们识别出三种不同的共识形成模式:低比例时促进人类主导的共识,中等比例时干扰收敛,高比例时恢复强共识,但转向代理主导的惯例。关键的是,这些模式不仅在收敛强度上不同,还在语义基础和表达形式上存在差异:人类主导的共识更具象、整体性,并基于共享的现实类比;而代理主导的共识更抽象、信息密度更低,且更几何分割化。机制上,代理影响力源于在表达空间中具有相似语言先验,且表达选择在回合间相对稳定;人类最初抵制来自被识别为AI的合作者的表达,但逐渐屈服于从众压力。这些发现表明,AI构成可塑造共识的出现、内容及感知合法性,使代理比例与透明度成为人机系统设计的重要变量。

原文摘要 · Abstract (English)

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.

人机协作共识形成语言模型

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。