• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation View PDF HTML (experimental)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. • References & Citations export BibTeX citation Loading…
Article Summaries:
- A new framework called MobCache aims to make large‑scale human mobility simulations using large language models (LLMs) more efficient. The system introduces a mobility‑aware cache that stores each reasoning step as a latent‑space embedding, allowing the model to reuse and recombine previously computed reasoning chains via a latent‑space evaluator. A lightweight decoder, trained with mobility‑law‑constrained distillation, translates these latent chains back into natural‑language agent actions. Experiments show that MobCache significantly reduces computational cost while preserving the fidelity of state‑of‑the‑art LLM‑based mobility simulations, benefiting applications in urban planning, epidemiology, and transportation analysis.
- Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation View PDF HTML (experimental)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 levera
Sources: