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

2026-02-17

AI Summary

This work addresses the challenge of scaling large language model (LLM)-driven human mobility simulation, which is hindered by prohibitive computational costs. To this end, the authors propose MobCache, a novel framework that introduces latent-space reasoning caching and recombination for the first time. The approach encodes LLM inference steps into reusable latent embeddings and leverages mobility pattern constraints to distill a lightweight decoder capable of efficiently generating natural-language behavior sequences. By caching and reusing latent representations while preserving semantic fidelity through constrained distillation, MobCache achieves substantial gains in simulation efficiency without compromising accuracy. The method matches the fidelity of state-of-the-art LLM-based approaches while enabling scalable, high-fidelity simulation of large-scale human mobility.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• large-scale human mobility simulation
• computational cost
• scalability
• LLM-based simulation
• efficiency

Innovation

• mobility-aware caching
• latent-space reasoning
• reconstructible cache
• mobility simulation
• LLM-based agents