用大模型代理模拟城市行为，让虚拟居民更像真实人群。
CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agents
- 代理以意图驱动决策，形成连贯的出行与活动计划。
- 通过学习习惯与偏好，提升个体行为真实度，微宏观指标更贴近现实。
- 支持数万代理并行，适合城市规划与政策评估场景。
大规模城市仿真在社会科学、交通安全和交通政策中具有关键作用。近期研究显示，将大语言模型作为代理进行提示，可生成城市尺度的逼真日常行为。然而，这些方法通常依赖少样本提示，导致代理复制大模型自身的行为先验，而非目标人群特征。本文提出CityReal，一个模块化的人类对齐城市仿真框架。CityReal将代理建模为意图驱动的决策者，追求连贯的出行与活动规划，而非孤立的步骤选择；它们通过经验与约束持续学习习惯与偏好。为提升群体层面的真实性，我们训练文本适配器，使代理决策与观测到的人口统计数据对齐。实验表明，CityReal在微观与宏观层面均显著提升与真实人类行为的匹配度。系统可扩展至数万代理，支持对人群密度、场所热度、出行流及福祉等在不同城市情景下的分析，提供可扩展的城市仿真与预测测试平台。
原文摘要 · Abstract (English)
Large-scale urban simulation plays a pivotal role in social science, traffic safety, and transportation policy. Recent work has shown that large language models, when prompted as agents, can generate lifelike daily routines at city scale. Yet these methods typically rely on few-shot prompting, causing agents to reproduce the LLM's behavioral priors rather than the target population. We introduce CityReal, a modular framework for human-aligned urban simulation. CityReal models agents as intention-driven decision makers that pursue coherent mobility and activity plans rather than isolated step-by-step choices. They adapt over time by learning habits and preferences based on experience and constraints. To improve population-level realism, we learn textual adapters for behavior modules that align agent decisions with observed population statistics. Experiments show that CityReal improves alignment with real-world human behavior at both micro and macro levels. Scaling to tens of thousands of agents, it supports analysis of crowd density, place popularity, mobility flows, and well-being under different urban scenarios, offering a scalable testbed for urban simulation and forecasting.
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。