用缓存提升大模型模拟人流效率，兼顾速度与真实度
Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation
- 将推理步骤编码为潜在空间嵌入，支持复用和重组
- 轻量解码器结合移动规律约束，效率提升显著
- 适合城市规划、疫情模拟等大规模人流仿真场景
大规模人类流动模拟对于理解人群移动模式及支持城市规划、疫情响应和交通分析等地理空间应用至关重要。近期工作将大语言模型（LLMs）作为人类代理，利用结构化推理生成真实流动行为，但其高计算成本限制了可扩展性。为此，我们设计了一种名为MobCache的移动感知缓存框架，通过可重构缓存实现高效的大规模人类流动模拟。该框架包含：(1) 推理组件，将每个推理步骤编码为潜在空间嵌入，并使用潜在空间评估器实现推理步骤的复用与重组；(2) 解码组件，采用基于移动规律约束的蒸馏训练的轻量级解码器，将潜在空间推理链转换为自然语言，从而在保持仿真保真度的同时显著提升效率。实验表明，MobCache在多个维度上显著提升效率，性能仍可媲美当前最优的基于LLM的方法。
原文摘要 · Abstract (English)
Simulating large-scale human mobility is fundamental to understanding population movement patterns and supporting real-world geospatial applications such as urban planning, epidemic response, 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。