个体层面的移动性预测是城市仿真、交通规划与政策分析的核心任务。监督式序列模型虽具备较高预测精度，但需针对特定任务进行训练，且在决策层面缺乏可解释性。近期基于大语言模型（LLM）的方法提升了可解释性，但大多依赖静态提示词与单次推理，难以在移动信号微弱或相互冲突时主动寻求额外证据。我们提出 \method{}——一种无需训练的、由大语言模型驱动的智能体框架，将下一位置预测建模为自适应证据调控的决策过程。\method{} 对常规情形通过基于历史规律的快速路径完成预测；对模糊情形则触发迭代式工具调用，整合近期轨迹、历史行为、驻留-移动概率及地理信息等多源证据。在三个移动性数据集上的实验表明，AgentMob 在所有无需训练的 LLM 方法中整体性能最优：GPT-5.4 在 BW 数据集上 Acc@1 达 71.42%，在 YJMob100K 上为 33.14%，在上海 ISP 数据集上为 33.50%。在 BW 数据集中非快速路径样本上，LLM 控制器将 Acc@1 从同工具统计基线的 30.65% 提升至 48.62%，验证了其核心优势在于通过自适应证据收集解决模糊预测问题。代码开源地址：https://github.com/Unknown-zoo/AgentMob。

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.