多模态推理的近期进展催生了能够解析图像、关联语言并执行结构化分析任务的智能体。然而，将此类能力拓展至遥感领域仍具挑战性，因模型需在空间尺度、地理结构及多光谱指数之上进行推理，同时保持连贯的多步逻辑。为填补这一空白，我们提出 \textit{OpenEarthAgent}——一个面向工具增强型地理空间推理的统一框架，其训练数据涵盖卫星影像、自然语言查询及结构化推理轨迹。OpenEarthAgent 不仅作为基准测试集，更构建了一套以统一可执行工具注册表与基于轨迹的策略学习为核心的连贯智能体架构。该框架将异构的视觉、光谱、GIS 及地理配准栅格操作标准化为一致的可调用接口，支持模块化编排与确定性执行。训练采用监督微调方式，在结构化推理轨迹上进行，并辅以确定性回放验证，以确保可执行性与空间正确性。配套语料库包含 14,538 个训练样本与 1,169 个评估样本，总计逾 107,000 个推理步骤，覆盖城市、环境、灾害与基础设施等领域，并整合 GIS 操作及 NDVI、NBR、NDBI 等指数分析。基于显式推理轨迹训练所得智能体，在多样化地球观测（EO）场景中展现出结构化推理能力、稳定的空间理解能力以及可解释的工具驱动行为。实验表明，本方法在强基线模型上实现持续性能提升，并在近期开源与闭源模型中具备竞争力。代码、数据及预训练模型均已公开：https://github.com/mbzuai-oryx/OpenEarthAgent

Recent progress in multimodal reasoning has enabled agents that interpret imagery, connect it with language, and execute structured analytical tasks. Extending these capabilities to remote sensing remains challenging, as models must reason over spatial scale, geographic structures, and multispectral indices while maintaining coherent multi-step logic. To address this gap, we introduce \textit{OpenEarthAgent}, a unified framework for tool-augmented geospatial reasoning trained on satellite imagery, natural-language queries, and structured reasoning traces. Beyond serving as a benchmark, OpenEarthAgent establishes a cohesive agentic architecture built around a unified executable tool registry and trajectory-based policy learning. The framework standardizes heterogeneous visual, spectral, GIS, and georeferenced raster operations under a consistent callable schema, enabling modular orchestration and deterministic execution. Training is performed via supervised fine-tuning on structured reasoning trajectories with deterministic replay validation to ensure executability and spatial correctness. The accompanying corpus comprises 14,538 training and 1,169 evaluation instances with over 107K reasoning steps, spanning urban, environmental, disaster, and infrastructure domains and incorporating GIS operations alongside index analyses such as NDVI, NBR, and NDBI. Grounded in explicit reasoning traces, the learned agent demonstrates structured reasoning, stable spatial understanding, and interpretable tool-driven behaviour across diverse EO scenarios. We report consistent improvements over a strong baseline and competitive performance against recent open and closed-source models. Our code, data and trained models are publicly available: https://github.com/mbzuai-oryx/OpenEarthAgent