Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation

2025/05/28 by Song, Yu-Lun, Tsern, Chung-En, Wu, Che-Cheng +5 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Multiagent Systems (cs.MA)

paper · doi:10.48550/arxiv.2505.21880

Abstract

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.

Cited by

• Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
• LLMs for Human Mobility: Opportunities, Challenges, and Future Directions

Related

• Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
• TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation
• CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation
• MobiVerse: Scaling Urban Mobility Simulation with Hybrid Lightweight Domain-Specific Generator and Large Language Models
• LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis