MobiVerse: Scaling Urban Mobility Simulation with Hybrid Lightweight Domain-Specific Generator and Large Language Models

TL;DR

MobiVerse is a hybrid simulation framework that combines lightweight domain-specific generators with large language models to efficiently model and adapt urban human mobility patterns at scale, supporting transportation planning and policy testing.

Contribution

It introduces a novel hybrid approach that enhances scalability and realism in urban mobility simulations by integrating lightweight generators with LLMs for dynamic, context-aware agent behavior.

Findings

Successfully simulated 53,000 agents in Los Angeles on a standard PC.

Demonstrated adaptive agent responses to environmental changes.

Maintained computational efficiency while increasing behavioral realism.

Abstract

Understanding and modeling human mobility patterns is crucial for effective transportation planning and urban development. Despite significant advances in mobility research, there remains a critical gap in simulation platforms that allow for algorithm development, policy implementation, and comprehensive evaluation at scale. Traditional activity-based models require extensive data collection and manual calibration, machine learning approaches struggle with adaptation to dynamic conditions, and treding agent-based Large Language Models (LLMs) implementations face computational constraints with large-scale simulations. To address these challenges, we propose MobiVerse, a hybrid framework leverages the efficiency of lightweight domain-specific generator for generating base activity chains with the adaptability of LLMs for context-aware modifications. A case study was conducted in Westwood, Los Angeles, where we efficiently generated and dynamically adjusted schedules for the whole population of approximately 53,000 agents on a standard PC. Our experiments demonstrate that MobiVerse successfully enables agents to respond to environmental feedback, including road closures, large gathering events like football games, and congestion, through our hybrid framework. Its modular design facilitates testing various mobility algorithms at both transportation system and agent levels. Results show our approach maintains computational efficiency while enhancing behavioral realism. MobiVerse bridges the gap in mobility simulation by providing a customizable platform for mobility systems planning and operations with benchmark algorithms. Code and videos are available at https://github.com/ucla-mobility/MobiVerse.