发表机构
University of Massachusetts（马萨诸塞大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究多智能体人群模拟中情感传播，通过感知 - 评估 - 表达循环及借鉴相关模型构建架构，在多场景评估，揭示情感传染动态，包括警报扩散、个性影响等，还发现评估步骤动态依赖后端。
AI 中文摘要
本文研究语言模型在多智能体人群模拟中的行为，聚焦情感在相互感知和评估的智能体间如何传播。每个智能体通过视觉、听觉和触觉通道感知邻居，根据其个性、记忆、当前情感状态和情境进行评估，由大语言模型执行评估并更新智能体内部情感状态及选择外在表达。架构中无直接传递情感状态的人工机制，智能体间影响通过感知 - 评估 - 表达循环产生。智能体表征借鉴大五人格模型和罗素情感环形模型。为限制延迟，低级转向和导航由独立于基于大语言模型的认知层的传统人群模拟器处理。在五种场景环境中评估该架构，结果表明系统在稀疏小群体中产生具有空间、时间和个性依赖结构的情感传染动态。警报从种子智能体作为传播前沿扩散，平均受警报比例稳定在非零平台，提示的个性分布决定模糊警报是否引发恐慌以及挑衅被解释为愤怒还是恐惧。还通过对提示变体、采样温度和四个模型后端的控制实验评估评估步骤，表明动态依赖于后端。
英文摘要
This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and appraise one another. Each agent perceives its neighbors through visual, auditory, and tactile channels, then appraises these perceptions in light of its prompted personality profile, memory, current affective state, and situational context. Appraisal is carried out by an LLM, which updates the agent's internal affective state and selects its outward expression. The architecture contains no hand-authored mechanism for directly transferring affective state between agents; instead, inter-agent influence arises through the perception-appraisal-expression loop. The agent representation draws on the Big Five personality model and Russell's circumplex model of affect. To limit latency, low-level steering and navigation are handled by a conventional crowd simulator operating independently of the LLM-based cognitive layer. We evaluate the architecture across five scenario environments spanning alarming, joyful, and neutral situations in different spatial layouts. The results show that the system produces emotional contagion dynamics with spatial, temporal, and personality-dependent structure in sparse, small crowds. Alarm spreads from seeded agents as a traveling front, the mean alarmed fraction settles at a nonzero plateau, and the distribution of prompted personality profiles determines whether an ambiguous alarm ignites panic and whether a provocation is interpreted as anger or fear. We further evaluate the appraisal step through controlled experiments across prompt variants, sampling temperatures, and four model backends, showing that the dynamics are backend-dependent.
Comments31 pages, 14 figures
