规划记录对地理区域施加限制，但其源文档通常仅提供间接的空间证据，而非机器可读的边界。我们提出 Plan2Map，一个包含 208 个案例的多模态基准，用于基于英国规划记录开展文档驱动的地理空间边界重建任务。给定一份原始规划文档，系统需仅依据公告文本、附表、地图图版、地图标注及边界注释，重建出有效的地理空间边界；参考 GeoJSON 标注被预留用于评估。我们提出 GeoPlanAgent，一种文档驱动、以地理空间工具为闭环组件的系统，将该任务分解为证据提取、定位、地图配准、边界分割、投影与验证六个子步骤。在 Plan2Map 上，GeoPlanAgent 取得 0.736 的平均交并比（IoU）和 0.904 的中位数 IoU，其中 67.8% 的预测结果达到或超过 0.8 IoU，显著优于直接使用视觉语言模型（VLM）生成 GeoJSON 的基线方法。诊断性分析表明，直接 VLM 预测仍不可靠；剩余误差主要集中于定位与地图配准环节；而监督式边界分割则显著提升了像素级掩码质量。Plan2Map 为从公开规划记录中开展多模态地理空间重建提供了具体的评测平台。项目主页：https://odeb1.github.io/Plan2Map_Project_Page/

Planning records define restrictions over geographic areas, but their source documents often provide only indirect spatial evidence rather than machine-readable boundaries. We introduce Plan2Map, a 208-case multimodal benchmark for document-grounded geospatial boundary reconstruction from UK planning records. Given only a source planning document, systems must reconstruct a valid geospatial boundary from notice text, schedules, map plates, map labels, and boundary annotations; the reference GeoJSON is held out for scoring. We propose GeoPlanAgent, a document-grounded, geospatial-tool-in-the-loop system that decomposes the task into evidence extraction, localisation, map registration, boundary segmentation, projection, and verification. On Plan2Map, GeoPlanAgent achieves 0.736 mean IoU and 0.904 median IoU, with 67.8\% of predictions at or above 0.8 IoU, substantially outperforming direct VLM-to-GeoJSON baselines. Diagnostic analysis shows that direct VLM prediction remains unreliable, while remaining errors are concentrated in localisation and map registration, and supervised boundary segmentation substantially improves pixel-level mask quality. Plan2Map provides a concrete testbed for multimodal geospatial reconstruction from public planning records. Project page: https://odeb1.github.io/Plan2Map_Project_Page/.