This study presents an innovative approach to urban mobility simulation by integrating a Large Language Model (LLM) with Agent-Based Modeling (ABM). Unlike traditional rule-based ABM, the proposed framework leverages LLM to enhance agent diversity and realism by generating synthetic population profiles, allocating routine and occasional locations, and simulating personalized routes. Using real-world data, the simulation models individual behaviors and large-scale mobility patterns in Taipei City. Key insights, such as route heat maps and mode-specific indicators, provide urban planners with actionable information for policy-making. Future work focuses on establishing robust validation frameworks to ensure accuracy and reliability in urban planning applications.
@article{arxiv.2505.21880,
title = {Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation},
author = {Yu-Lun Song and Chung-En Tsern and Che-Cheng Wu and Yu-Ming Chang and Syuan-Bo Huang and Wei-Chu Chen and Michael Chia-Liang Lin and Yu-Ta Lin},
journal= {arXiv preprint arXiv:2505.21880},
year = {2025}
}
Comments
8 pages, 8 figures. This paper is reviewed and accepted by the CUPUM (Computational Urban Planning and Urban Management) Conference held by University College London (UCL) in 2025