增强人类移动预测：基于空间感知的LLM多智能体系统
Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems
- University of California & Santa Barbara（加州大学圣塔芭芭拉分校）
- San Diego State University（圣地亚哥州立大学）
- Politecnico di Milano（米兰理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对LLM忽略空间上下文导致移动预测不准的问题，提出三阶段多智能体框架，结合行为模式与空间约束，在NYC基准上Hit@1提升达493%。
AI中文摘要：
预测用户的下一个兴趣点（POI）是人类移动建模中的一项任务，然而基于大语言模型（LLM）的方法侧重于从先前的移动记录中进行语义推理，而忽略了现实世界的空间上下文。然而，人类移动本质上是由空间认知塑造的，包括地理距离和邻域上下文。这一问题因先前证据表明LLM通常在空间推理任务（包括距离估计和地理偏差预测）中表现不佳而进一步加剧。为解决这些局限性，我们提出了我们的框架，这是一个多智能体LLM框架，将下一个POI预测分解为三个阶段：首先，模式提取智能体（Pattern Extraction Agent）从轨迹历史中捕获时间和类别移动模式；其次，空间推理智能体（Spatial Reasoning Agent）通过将行为偏好与现实世界空间约束（包括地理距离、路网距离和邻域归属）相结合来构建候选活动选择；第三，决策综合智能体（Decision Synthesis Agent）整合行为模式和空间推理以进行最终预测。在NYC基准数据集上使用两个LLM后端的实验显示，相对于基线方法有改进，Hit@1最高提升493%，Hit@5相对提升37%。消融实验表明，将邻域归属与基于距离的特征相结合通常优于仅使用距离的设置，并且空间推理智能体通过将行为偏好与现实世界空间约束相结合，在最终预测中发挥关键作用，尤其是对于较小的模型。总体而言，结果强调了空间推理在移动预测中的重要性。准确的下一个POI预测需要将行为模式与明确的现实世界空间约束相结合，而多智能体分解为组织这些形式的上下文提供了有效的结构。
英文摘要：
Predicting a user's next POI is a task in human mobility modeling, yet LLM-based approaches focus on semantic reasoning from previous mobility records, while neglecting real-world spatial context. However, human mobility is inherently shaped by spatial cognition, including geographic distance and neighborhood context. This issue is further compounded by prior evidence that LLMs often struggle with spatial reasoning tasks, including distance estimation and geographically biased prediction. To address these limitations, we propose our framework, a multi-agent LLM framework that decomposes next-POI prediction into three stages: Firstly, a Pattern Extraction Agent that captures temporal and categorical mobility patterns from trajectory history; Secondly, a Spatial Reasoning Agent that structures candidate activity choices by combining behavioral preferences with real-world spatial constraints, including geographic distance, road network distance, and neighborhood affiliation; and Thirdly, a Decision Synthesis Agent that integrates behavioral patterns and spatial reasoning for final prediction. Experiments on the NYC benchmark dataset with two LLM backbones show improvements over baseline methods, with up to 493% Hit@1 improvement and 37% relative improvement in Hit@5. Ablations show that combining neighborhood affiliation with distance-based features generally outperforms distance-only settings, and that the Spatial Reasoning Agent plays a crucial role in final prediction by integrating behavioral preferences with real-world spatial constraints, especially for smaller models. Overall, the results highlight the importance of spatial reasoning in mobility prediction. Accurate next-POI prediction requires combining behavioral patterns with explicit real-world spatial constraints, and multi-agent decomposition provides an effective structure for organizing these forms of context.
