Google Earth AI 是一系列地理空间 AI 模型及其编排智能体的集合。本文介绍了该智能体，即 Google Earth AI 的地理空间推理智能体（GRA），这是一个由 Gemini 驱动的研究系统，结合地理空间数据源、基础模型和工具来回答关于地球的问题。GRA 将这些组件组织为模块化的领域技能，并配合前置地理空间规划，将复杂查询分解为多阶段工作流。评估此类系统具有挑战性：现实世界问题存在多种有效工作流，需要在大型目录中进行数据发现，且依赖不断演变的基准真值。我们引入了两个基准测试并发布其开发集。GeoExpertQueries 基于从业者用例并由地理空间专家完善，提出复杂的分析问题；每个问题均配有来自三位独立专家的共识黄金工作流，并通过经过人工验证的工具无关自动评分器进行评分。GeoKTools 包含带有确定性参考求解器的模板化查询，系统地改变所需工具类型的数量。我们还使用了两个外部基准测试 CBGB 和 UnivEARTH；我们发现后者已饱和。为了隔离 GRA 的工具及其智能体编排的贡献，我们比较了四种配置，每种配置均使用 Gemini 3.1 Pro 和 3.8 Flash：独立 LLM、配备基本工具的 LLM、配备 GRA 技能和工具但无前置规划和执行指导的 LLM，以及完整的 GRA。仅配备基本工具时，高级模型在模板化查询上能恢复大部分答案，但在开放式问题上仅满足少量专家工作流；而 GRA 在两者上表现良好。最大的性能提升来自 GRA 的技能与工具；在开放式问题上，其规划和执行指导进一步提升了 Gemini 3.8 Flash 的性能，使其以更低成本达到或超过 Pro 的效果。

Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial Reasoning agent (GRA), a Gemini-powered research system that combines geospatial data sources, foundation models, and tools to answer questions about our planet. GRA organizes these into modular domain skills and pairs them with upfront geospatial planning to decompose complex queries into multi-stage workflows. Evaluating such systems is hard: real-world problems admit multiple valid workflows, require data discovery across large catalogs, and rely on evolving ground truth. We introduce two benchmarks and release their development splits. GeoExpertQueries poses complex analytical problems grounded in practitioner use cases and refined by geospatial experts; each is paired with a consensus golden workflow from three independent experts and scored by a human-validated, tool-agnostic autorater. GeoKTools consists of templated queries with deterministic reference solvers that systematically vary the number of required tool types. We also use two external benchmarks, CBGB and UnivEARTH; the latter we find to be saturated. To isolate the contribution of GRA's tools and its agentic orchestration, we compare four configurations, each with Gemini 3.1 Pro and 3.8 Flash: a standalone LLM, the LLM with basic tools, the LLM with GRA's skills and tools but without its upfront planning and execution guidance, and GRA itself. With at most basic tools, an advanced model recovers much of the answer on templated queries but satisfies only a small fraction of the expert workflows on open-ended problems; GRA performs well on both. The largest step comes from GRA's skills and tools; on open-ended problems, its planning and execution guidance add a further gain with Gemini 3.8 Flash, letting Flash match or exceed Pro at lower cost.