CityBehavEx：一个可扩展且经过实证验证的基于大语言模型的城市模拟平台
CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform
- UTFPR（巴拉那联邦理工大学）
- Inria（法国国家信息与自动化研究所）
- University of Toronto（多伦多大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
CityBehavEx平台针对基于大语言模型的城市模拟器扩展成本高和验证薄弱问题，结合人类出行模型与交叉编码器，实现大规模模拟，能生成更贴合现实的出行模式，还允许用户进行多种操作及验证。
AI中文摘要：
近期基于大语言模型的多智能体城市模拟器虽能生成语义丰富的城市日常，但扩展成本高且与实证出行模式的验证薄弱。我们提出CityBehavEx，一个交互式的基于大语言模型的城市模拟平台，可扩展到城市规模人口，能检查智能体行为，支持实证验证，并生成更符合现实世界空间、时间和语义分布的出行模式。它将既定的人类出行模型与微调的交叉编码器相结合，而非为每个智能体动作调用大语言模型。在单个消费级GPU上，一小时内对10万个智能体进行75天的案例研究证明了其可大规模模拟。该平台允许用户定义模拟区域、启动实验、检查轨迹和活动踪迹、调试不现实行为，并根据现实世界的出行、时间使用和语义指标验证生成的日常。
英文摘要：
Recent LLM-based multi-agent urban simulators can generate semantically rich city routines, but they remain costly to scale and are often weakly validated against empirical mobility patterns. We present CityBehavEx, an interactive LLM-assisted urban simulation platform that scales to city-size populations, exposes agent behavior for inspection, supports empirical validation, and generates mobility patterns that better match real-world spatial, temporal, and semantic distributions. Instead of invoking large language models for every agent action, CityBehavEx combines established human mobility models with fine-tuned cross-encoders that estimate semantic alignment between agent profiles, schedules, and activity transitions. This design enables large-scale simulations, as demonstrated in a case study of 100,000 agents over 75 days in under one hour on a single consumer GPU. The platform allows users to define simulation regions, launch experiments, inspect trajectories and activity traces, debug unrealistic behaviors, and validate generated routines against real-world mobility, time-use, and semantic metrics.
