发表机构
Woven by Toyota（丰田编织公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CityReal是人类对齐城市模拟的模块化框架，将智能体建模为意图驱动的决策者，通过文本适配器提升人群行为对齐度，可扩展至数万个智能体，为城市模拟与预测提供可扩展测试平台。
AI 中文摘要
大规模城市模拟在社会科学、交通安全和交通政策制定中发挥关键作用。近期研究表明，将大语言模型（LLM）作为智能体进行提示时，可生成城市规模的逼真日常活动，但这些方法通常依赖少样本提示，导致智能体重现LLM的行为先验而非目标人群的真实行为。本文提出CityReal，一个用于人类对齐城市模拟的模块化框架。CityReal将智能体建模为意图驱动的决策者，追求连贯的出行与活动计划，而非孤立的分步选择；智能体可根据经验和约束学习习惯与偏好，随时间自适应调整。为提升人群层面的逼真度，本文为行为模块学习文本适配器，使智能体决策与观测到的人群统计数据对齐。实验显示，CityReal在微观和宏观层面均提升了与现实人类行为的对齐度，可扩展至数万个智能体，支持分析不同城市场景下的人群密度、场所热度、出行流及福祉，为城市模拟与预测提供可扩展的测试平台。
英文摘要
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.
