智能体物理学：统计力学预测AI智能体的集体行为
Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
AI总结：
该研究以10000余个语言模型智能体社区为对象，用统计力学模型将其集体动态分为三种状态，预测个体轨迹优于基线，揭示了AI智能体集体行为遵循可预测动力学规律。
AI中文摘要：
AI智能体越来越多地作为交互系统的一部分运行，而非独立运作。当智能体交换信息并共同做出决策时，它们的交互可以提升集体推理能力，但也可能产生从众、极化或放大共同偏见等问题。因此，理解和预测这些集体动态对于设计有效且对齐的多智能体系统至关重要。本研究分析了超过10000个语言模型智能体的社区，这些智能体会就客观数学问题和主观政治陈述反复交换消息并修正观点。尽管行为存在巨大多样性，但个体和群体动态可分为三种特征状态：无差别、极化和共识。AI智能体初始处于无差别状态，随着交互逐渐建立信念。在客观问题上，沟通提升了集体准确性；而在主观问题上，沟通常使群体观点向政治光谱的右侧偏移。本研究用统计力学形式主义解释这些观察结果，其中智能体随机倾向于更低的社会压力。仅给定初始观点，该模型可预测个体轨迹，优于所有标准基线，能泛化到未见过的社区图，并复现观察到的群体原型分布。拟合的模型参数揭示了关键观察背后的机制：i）社区运行在临界社会温度以下，这解释了信念的建立；ii）吸引力关系超过排斥关系，这有利于共识；iii）持有正确答案的智能体具有最强的吸引力，这推动了求真。总体而言，研究结果表明，AI智能体的集体行为与其他复杂系统一样，遵循紧凑且可预测的动力学规律。
英文摘要：
AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.
