Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation

TL;DR

This paper introduces a novel urban mobility simulation framework that combines Large Language Models with Agent-Based Modeling to generate realistic, diverse agent behaviors and large-scale mobility patterns, aiding urban planning.

Contribution

It presents the first integration of LLMs into large-scale urban mobility simulation, enhancing agent diversity and realism beyond traditional rule-based methods.

Findings

Generated synthetic population profiles and routes using LLMs.

Produced detailed mobility patterns and heat maps for Taipei City.

Provided actionable insights for urban planning and policy-making.

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.