Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Yu-Lun, Tsern, Chung-En, Wu, Che-Cheng, Chang, Yu-Ming, Huang, Syuan-Bo, Chen, Wei-Chu, Lin, Michael Chia-Liang, Lin, Yu-Ta
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913923418030080
author Song, Yu-Lun
Tsern, Chung-En
Wu, Che-Cheng
Chang, Yu-Ming
Huang, Syuan-Bo
Chen, Wei-Chu
Lin, Michael Chia-Liang
Lin, Yu-Ta
author_facet Song, Yu-Lun
Tsern, Chung-En
Wu, Che-Cheng
Chang, Yu-Ming
Huang, Syuan-Bo
Chen, Wei-Chu
Lin, Michael Chia-Liang
Lin, Yu-Ta
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21880
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation
Song, Yu-Lun
Tsern, Chung-En
Wu, Che-Cheng
Chang, Yu-Ming
Huang, Syuan-Bo
Chen, Wei-Chu
Lin, Michael Chia-Liang
Lin, Yu-Ta
Multiagent Systems
Artificial Intelligence
Computation and Language
Computers and Society
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.
title Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation
topic Multiagent Systems
Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2505.21880