Guiding LLM-Based Human Mobility Simulation with Mobility Measures from Shared Data

TL;DR

This paper introduces M2LSimu, a framework that guides large language models to generate realistic human mobility patterns by using shared data-derived mobility measures to ensure population-level behaviors are accurately modeled.

Contribution

The paper presents a novel mobility measures-guided multi-prompt adjustment framework that improves LLM-based human mobility simulation by incorporating population-level coordination.

Findings

M2LSimu outperforms existing LLM-based methods on public datasets.

The framework effectively captures collective mobility behaviors.

Guided prompt adjustment enhances the realism of simulated trajectories.

Abstract

Large-scale human mobility simulation is critical for many science domains such as urban science, epidemiology, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility trajectories by modeling individual-level cognitive processes. However, these approaches generate individual mobility trajectories independently, without any population-level coordination mechanism, and thus fail to capture the emergence of collective behaviors. To address this issue, we design M2LSimu, a mobility measures-guided multi-prompt adjustment framework that leverages mobility measures derived from shared data as guidance to refine individual-level prompts for realistic mobility generation. Our framework applies coarse-grained adjustment strategies guided by mobility measures, progressively enabling fine-grained individual-level adaptation while satisfying multiple population-level mobility objectives under a limited budget. Experiments show that M2LSimu significantly outperforms state-of-the-art LLM-based methods on two public datasets.