预测用户的下一个兴趣点（POI）是人类移动性建模中的一项任务，然而基于大语言模型（LLM）的方法侧重于从既往移动记录中进行语义推理，却忽视了现实世界的空间上下文。事实上，人类移动性本质上受空间认知的影响，包括地理距离和邻域上下文。此外，已有证据表明LLM在空间推理任务（如距离估计和具有地理偏差的预测）中往往表现不佳，这进一步加剧了上述问题。为解决这些局限性，我们提出了一个多智能体LLM框架，将下一POI预测分解为三个阶段：首先，模式提取智能体从轨迹历史中捕捉时间和类别移动模式；其次，空间推理智能体通过结合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）来构建候选活动选择；最后，决策综合智能体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种LLM骨干网络进行的实验显示，该方法优于基线方法，Hit@1提升高达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，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，在最终预测中起着关键作用，尤其对于较小规模的模型而言。总体而言，结果凸显了空间推理在移动性预测中的重要性。准确的下一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。

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.