面向高效且基于证据的移动预测：基于LLM驱动的智能体
Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent
- The University of Tokyo（东京大学）
- Huazhong University of Science and Technology（华中科技大学）
- University of New South Wales, Sydney（新南威尔士大学（悉尼））
- LocationMind Inc.（LocationMind公司）
- Southern University of Science and Technology（南方科技大学）
- Jilin University（吉林大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出一种无需训练的LLM驱动智能体框架AgentMob，通过自适应证据收集机制解决移动预测中的模糊情况，在多个数据集上达到最优性能。
AI中文摘要：
个体层面的移动预测是城市模拟、交通规划和政策分析的核心。监督序列模型实现了高精度，但需要任务特定训练且决策透明度有限。最近的基于LLM的方法提高了可解释性，但大多依赖静态提示和单次推理，限制了在移动信号弱或冲突时寻求额外证据的能力。我们提出\method{}，一种无需训练的LLM驱动智能体框架，将下一位置预测建模为自适应证据控制的决策制定。\method{}通过基于历史规律性的快速路径处理常规情况，而模糊情况则触发对近期轨迹、历史行为、停留-移动可能性和地理证据的迭代工具使用。在三个移动数据集上，AgentMob在无需训练的基于LLM的方法中实现了最强的整体性能，GPT-5.4在BW上达到71.42%的Acc@1，在YJMob100K上达到33.14%，在上海ISP上达到33.50%。在BW的非快速路径案例中，LLM控制器相比相同工具的统计基线将Acc@1从30.65%提高到48.62%，表明其主要优势在于通过自适应证据收集解决模糊预测。我们的代码可在https://github.com/Unknown-zoo/AgentMob获取。
英文摘要：
Individual-level mobility prediction is central to urban simulation, transportation planning, and policy analysis. Supervised sequence models achieve strong accuracy but require task-specific training and offer limited decision-level transparency. Recent LLM-based methods improve interpretability, yet mostly rely on static prompts and single-pass inference, limiting their ability to seek additional evidence when mobility signals are weak or conflicting. We propose \method{}, a training-free LLM-driven agent framework that formulates next-location prediction as adaptive evidence-controlled decision making. \method{} resolves routine cases through a fast path based on historical regularity, while ambiguous cases trigger iterative tool use over recent trajectories, historical behavior, stay-move likelihood, and geographical evidence. Across three mobility datasets, AgentMob achieves the strongest overall performance among training-free LLM-based methods, with GPT-5.4 reaching 71.42\% Acc@1 on BW, 33.14\% on YJMob100K, and 33.50\% on Shanghai ISP. On BW non-fast-path cases, the LLM controller improves Acc@1 from 30.65\% to 48.62\% over a same-tool statistical baseline, showing that its main benefit lies in resolving ambiguous predictions through adaptive evidence gathering. Our code is available at https://github.com/Unknown-zoo/AgentMob.
