TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation

TL;DR

TrajLLM introduces a modular framework utilizing Large Language Models to generate realistic human mobility simulations, addressing privacy and cost issues of traditional models with scalable, interpretable, and adaptable routines for urban planning and social analysis.

Contribution

This work presents a novel hierarchical LLM-based framework that integrates demographic data and psychological profiles for realistic, scalable human mobility simulation.

Findings

LLM-driven simulations match real-world movement patterns.

The framework enables dynamic persona and activity generation.

Preliminary results show potential for urban planning and public health applications.

Abstract

This work leverages Large Language Models (LLMs) to simulate human mobility, addressing challenges like high costs and privacy concerns in traditional models. Our hierarchical framework integrates persona generation, activity selection, and destination prediction, using real-world demographic and psychological data to create realistic movement patterns. Both physical models and language models are employed to explore and demonstrate different methodologies for human mobility simulation. By structuring data with summarization and weighted density metrics, the system ensures scalable memory management while retaining actionable insights. Preliminary results indicate that LLM-driven simulations align with observed real-world patterns, offering scalable, interpretable insights for social problems such as urban planning, traffic management, and public health. The framework's ability to dynamically generate personas and activities enables it to provide adaptable and realistic daily routines. This study demonstrates the transformative potential of LLMs in advancing mobility modeling for societal and urban applications. The source code and interactive demo for our framework are available at https://github.com/cju0/TrajLLM.