Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation

TL;DR

This paper introduces MobCache, a caching framework that enhances the scalability and efficiency of large language model-based human mobility simulations without sacrificing accuracy.

Contribution

MobCache employs reconstructible caches and latent-space reasoning to enable efficient large-scale human mobility simulation using LLMs.

Findings

Significantly improves simulation efficiency

Maintains comparable fidelity to state-of-the-art methods

Reduces computational costs for large-scale simulations

Abstract

Large-scale human mobility simulation is critical for applications such as urban planning, epidemiology, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility behaviors using structured reasoning, but their high computational cost limits scalability. To address this, we design a mobility-aware cache framework named MobCache that leverages reconstructible caches to enable efficient large-scale human mobility simulations. It consists of: (1) a reasoning component that encodes each reasoning step as a latent-space embedding and uses a latent-space evaluator to enable the reuse and recombination of reasoning steps; and (2) a decoding component that employs a lightweight decoder trained with mobility law-constrained distillation to translate latent-space reasoning chains into natural language, thereby improving simulation efficiency while maintaining fidelity. Experiments show that MobCache significantly improves efficiency across multiple dimensions while maintaining performance comparable to state-of-the-art LLM-based methods.