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.

翻译：个体层面的移动性预测是城市模拟、交通规划和政策分析的核心。监督序列模型虽能实现高精度，但需要特定任务的训练，且决策层透明度有限。近期基于大语言模型的方法提升了可解释性，但大多依赖静态提示和单次推理，在移动信号较弱或矛盾时难以寻求额外证据。我们提出\method{}，一种无需训练的大语言模型驱动智能体框架，将下一位置预测建模为自适应性证据控制的决策过程。\method{}通过基于历史规律性的快速路径解决常规情形，而在模糊情形下，则针对近期轨迹、历史行为、停留-移动可能性及地理证据触发迭代工具使用。在三个移动数据集上，AgentMob在无需训练的基于大语言模型方法中取得最优整体性能：GPT-5.4在BW数据集上达到71.42%的Acc@1，在YJMob100K上达到33.14%，在上海ISP上达到33.50%。在BW非快速路径情形中，大语言模型控制器相比同工具统计基线将Acc@1从30.65%提升至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。我们的代码开源在https://github.com/Unknown-zoo/AgentMob。