发表机构
School of Transportation and Logistics, Southwest Jiaotong University; Fujian Police College（西南交通大学交通运输与物流学院; 福建警察学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出基于LLM的智能体框架，通过人格条件提示和记忆知识图谱建模移动威胁下的异构疏散行为，实验表明信息获取显著影响疏散成功率。
AI 中文摘要
在移动威胁下对异构疏散行为进行建模是困难的，因为人类的感知、记忆和证据评估无法被固定规则很好地捕捉。我们提出了一种新颖的基于LLM的智能体框架来表示这些内部决策过程。每个行人智能体感知一个私有的符号ASCII视图，维护一个仅从个体观察中推导出的基于记忆的知识图谱，并在共同的采样配置下通过人格条件提示做出决策。一个带有无状态记忆的压缩决策上下文在跨回合保留试错经验的同时排除推理痕迹，并且一个验证引擎通过仅在观察到的地形上执行路线来将行为选择与物理可行性分离。我们在一个模拟的公共广场中，在八个配对随机区组内评估了八种人格组合。可用出口知识与疏散成功密切相关：拥有此类知识的智能体中89.5%成功疏散，而没有此类知识的智能体中仅有1.05%成功疏散。人格组合在对记忆威胁证据的评估方面也存在差异：危险评估的比例变化了0.265，而高紧迫性、低直接性的决策范围从11.41%到34.33%不等。在直接看到威胁后，反应趋于一致，99.6%的评估将情况归类为危险。在99.8%的决策中选择了移动。总体而言，疏散结果与信息获取密切相关，而疏散时间与空间几何、信息和情感共同相关。该框架提供了一种可审计的方法，通过人格条件化的LLM智能体在人群疏散模拟中生成内生的行为异构性。
英文摘要
Modeling heterogeneous evacuation behavior under a moving threat is difficult because human perception, memory, and evidence evaluation are not well captured by fixed rules. We propose a novel LLM-powered agent-based framework to represent these internal decision processes. Each pedestrian agent perceives a private symbolic ASCII view, maintains a Memory-based Knowledge Graph derived solely from individual observations, and makes decisions through persona-conditioned prompts under a common sampling configuration. A compressed decision context with stateless memory preserves trial-and-error experience across turns while excluding reasoning traces, and a validation engine separates behavioral choice from physical feasibility by executing routes only over observed terrain. We evaluated eight personality compositions in eight paired randomized blocks within a simulated public plaza. Usable-exit knowledge was strongly associated with evacuation success: 89.5% of agents possessing such knowledge evacuated, compared with 1.05% of those without it. Personality compositions also differed in their evaluation of remembered threat evidence: the proportion of danger assessments varied by 0.265, while high-urgency, low-directness decisions ranged from 11.41% to 34.33%. After direct threat sightings, responses converged, with 99.6% of assessments classifying the situation as dangerous. Movement was selected in 99.8% of decisions. Overall, evacuation outcomes were strongly associated with information access, while evacuation time was jointly associated with spatial geometry, information, and affect. The framework provides an auditable approach to generating endogenous behavioral heterogeneity through persona-conditioned LLM agents in crowd-evacuation simulations.
