2026年10月14日 (英语).
著名工程师Shravya Shetty和Google研究产品主任Luke Barrington
在一份新的技术报告中，我们展示了如何将特定域的基础模型、空间工具和前期规划结合起来，使地理空间理性agent能够进行复杂的空间分析和行星预测，而孤立的LLMs是无法做到的。 在与合作伙伴进行有希望的测试之后，我们也正在通过Ask Google Earth和Agent对Agent(A2A)服务扩大实验性的agent访问。
当我们推出 Google Earth AI时，我们分享了一套地理空间基础模型——涵盖遥感，天气，洪涝水文学和人口动态——以及一个初步的原型，显示Gemini动力的agent如何将这些模型连接起来，回答跨模式的问题。
此后，我们把地理空间理性agent从早期的概念发展成为一个能力强得多的实验系统，用于跨行星尺度数据的多步地理空间推理和定制预测模型的自主培训。 今天，我们分享三个最新情况：
- 关于地理空间推理的新技术报告：我们提出对四个基准测试的系统评价，包括GeoKTools和GeoExpertQueries，两个我们开发的新的基准测试，并正在向研究人员发布，以测试他们自己的地理空间推理agents. 我们的成果量化了地球AI的专门工具的价值
- 真实世界伙伴测试的洞察力：在过去几个月中，我们邀请了一小批社会影响和商业伙伴组织——包括世界卫生组织(卫生组织)非洲区域办事处、有需要者、给予直接援助者、Milken研究所和WPP——测试agent，以支持它们自己的现实世界工作流程，例如疾病爆发调查、备灾和清洁能源筛选。
- 扩大对Google地球和Google云的早期访问：我们正在扩大多步骤地理空间分析和行星预测的实验访问。 我们为询问Google地球，也为开发者提供agent到agent API的早期访问
通用的LLMs和标准编码工具与现实世界的空间问题发生斗争，因为行星数据集庞大，有专门的地图和卫星格式，需要仔细的多步骤规划才能准确结合。 为了在实践中处理复杂的空间工作流程，我们的agent 带来结合了四个关键能力：
agent将Gemini与地球AI的基础模型——包括WeatherNext，洪水预报，人口动态基础模型(PDFM),AlphaEarth基金会和遥感基金会——与来自Google地图平台(如位置信息，路由，空气质量，屋顶太阳潜力),Google地球引擎，数据常识和Google数据集搜索的信息连接起来。
地球AI能力被包装为模块化技能，agent仅在用户质疑需要时才调用。 在运行复杂操作之前，agent会构建一个分步分析计划，在局部覆盖范围稀少时选择适当的回落数据集，并在专用的工作空间中处理大地图层。 这种方法避免了agent上下文与大量的空间数据，同时保持了准确性和跟踪数据归属性。 每个响应显示 agent的计划和所使用的数据源，因此专家可以检查假设或替代数据集。
各组织很少仅依靠公共数据。 用户现在可以通过地理空间理性agent API输入自己的数据集作为CSV电子表格，自定义地图边界(GeoJSON)，或云表。 然后用户可以要求agent与地球AI的全球模型和目录一起加入他们的私人地点。
除了回答复杂的分析问题之外，agent还赋予我们最近的宣布行星预测引擎以权力。 考虑到用户的本地结果数据，如区域疾病率、作物产量或断电，agent自动选择相关的人口和环境信号，将我们的人口动态透视和定制卫星嵌入(Google地图平台产品分别建在PDFM和AlphaEarth基金会上)引信，并培训经过验证的机器学习模型，用于空间预测、超分辨率缩小尺度和预测。 在最近的公共卫生研究中，把这些人口和卫星信号结合起来，使对健康结果的预测比人口基线提高了12%，并使得能够以更细的空间分辨率绘制8X。
为了衡量特定域工具和前期规划对地理空间推理的影响，我们的技术报告比较了跨越Gemini 3.8 Flash和Gemini 3.1 Pro的4个agent配置：(1) 一个独立的LLM, (2) LLM具有基本的网络搜索和地图定位工具，(3) LLM具有地球AI工具(如遥感基础和WeatherNext 3)，但没有前期规划，以及(4) 完整的地理空间理性agent，它开始每个查询时都有一个专门的规划阶段，其原因在于它是否有能力评估其所能做和不能做，并设定获得答案所需的检索和处理阶段。
该评价涵盖四个基准测试，涵盖专家级的开放式分析、多工具组合以及社区开发的具有决定性答案的地理空间问题。 CBGB和UnivEarth是两个外部开发的基准测试，分别测试地理空间代码生成和问答。 为了测试agents对于超越单个问题或使用案例的挑战性任务，我们开发了两个新的基准测试。 GeoExpertQueries 推出复杂，现实世界的查询，使用专家撰写的黄金工作流程，收集危机应对能力，选址和公共卫生等领域的最佳做法分析。 GeoKTools包含有可核查答案的模板化查询，每个查询需要正确选择和使用1至4个独特的地理空间工具。 该套套件的覆盖范围大大超过以往对地理空间推理系统的评价。 为了加快地理空间agents的研发，我们全面发布了我们两个新基准测试的开发分割。
有两个关键的外卖从我们的评价中突出出来：第一，特定领域的技能对空间推理至关重要。 agent只拥有基本工具(网络搜索，地图定位和代码执行)，在定量空间任务上挣扎。 将agent配备为地球AI技能，驱动了GeoExpertQueries,GeoKTools，和CBGB之间的重大跳跃。 唯一的例外是UnivEarth，甚至一个独立的LLM的得分也高达93.6%，这可能是因为源头NASA的文章和答案可以在公共网上找到。
第二，前期规划解锁开放的，现实世界的工作流程。 虽然仅地球AI技能就足以完成CBGB和GeoKTools中较窄的任务，但在GeoExpertQueries中解决开放式问题需要先期规划，使agent在多步骤分析中保持正轨，防止它作出不可靠的假设或采取诸如使用网络搜索而不是空间工具等快捷方式。
使用 Gemini 3.8 Flash 对所有四个基准测试的分数下表：
技术报告还讨论了局限性。 GeoExpertQueries的分数来自一个将agent的性能与专家工作流程进行比较的自动解析器，该工作流程定义了分析应该采取的步骤，而不是正确的最终答案。 因此，我们认为agent的产出是专家们审查和发展的有力初稿，而不是最后的答案。
为了评估这项研究如何转化为现实世界的挑战，我们让一小群伙伴提前测试实验性agent 他们最棘手的问题。 以下概述它们如何将地球AI付诸行动：
世界卫生组织(WHO AFRO)和刚果民主共和国的INRB：在2026年刚果民主共和国埃博拉爆发之初，WHO AFRO在达喀尔的应急准备和反应中心利用地理空间理性agent绘制了偏远的采矿走廊图，通过交叉参照森林损失(从卫星图像)、采矿地点(从地图和网络数据)和人口数据，这些走廊的接触风险和人员流动性都很高。 在几分钟内，小组确定了48个暴露的住区，并查明了45 500多名处于危险中的人——这一过程通常需要几周时间。 这使当地应急人员能够积极主动地部署流动实验室和协调边境监视。 与此同时，刚果民主共和国国家生物医学研究所(INRB)的流行病模型和情报股(UMIE)利用行星预测引擎来估计埃博拉扩散到未感染地区的风险。 通过将流动流动与历史案例趋势以及地球AI模型和数据集相结合，这些每周的见识为协调员提供了在案件到达之前的关键规划时间。
- “象矿工这样的流动人口比传统的纸质监测能够追踪的速度快，造成危险的盲点。 地球AI用卫星和移动信号来填补这些空白——将我们从被动地追逐一种病毒转移到积极预报它接下来会袭击的地方。” Etien Koua博士，卫生组织AFRO应急准备和反应方案地区经理和中心协调员(观看录像)
- 需要帮助的人：地理空间推理有助于将自然灾害预测与人口和图像信息结合起来，将分析人员的重点从数据处理转向提供见解：
实验地理空间理性agent帮助我们分析14条历史气旋路径，以数分钟而不是数天的人工GIS工作来确定高接触度村庄，- 阿隆索·冈萨雷斯，地理信息系统和遥感协调员
在密西西比州热带气旋Mala和基准测试龙卷风破坏期间，各小组上传了定制地图边界，以快速计算风速区的人口暴露情况，将危机范围从几天缩短到几分钟。
- WPP：使用地理空间推理将人口动态透视与其专有数据连接起来。 他们的案例研究展示了地球AI的洞察力如何提高了地理空间营销运动的性能，同时维护了他们数据的隐私。
Milken Institute：预开发团队利用agent将自己的1500+候选建筑名单与Google地图平台的太阳能API和人口普查数据结合起来，以筛选用于建设社区复原力枢纽的地点，同时考虑到屋顶的太阳能潜力，流动性数据，附近的中转枢纽，气候风险，以及联邦投资区的资格。
与这些合作伙伴的早期测试有助于我们评估和扩大agent的地理空间技能，推动我们最近增加了道路网络线路，支持更大的用户加载数据集，更好地发现权威的本地数据来源。
今天，我们正在扩大地球人工智能的研究能力，以收集更多关于这些实验地理空间推理能力的反馈。 我们向少数早期用户提供：
- 询问Google Earth：在询问Google Earth直接内部预览扩展的深度分析能力。 这提供了一个交互聊天体验，你可以用自然语言询问复杂的空间问题，在Google地球项目中分析数据——包括你自己的数据——并直接在地图上探索视觉结果。
——地理空间理性Agent API：对于需要自定义的，做自己的集成以驱动自定义工作流程的开发团队，我们提供实验性无头Agent至Agent(A2A)服务。 早期的伴侣可以共鸣
本文由 AI宝盒自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
October 14, 2026
Shravya Shetty, Distinguished Engineer, and Luke Barrington, Product Director, Google Research
In a new technical report, we demonstrate how combining domain-specific foundation models, spatial tools, and upfront planning enables a Geospatial Reasoning agent to carry out complex spatial analysis and planetary prediction that standalone LLMs can’t. Following promising tests with partners, we’re also expanding experimental agent access via Ask Google Earth and an Agent-to-Agent (A2A) service.
When we introduced Google Earth AI, we shared a suite of geospatial foundation models — spanning remote sensing, weather, flood hydrology, and population dynamics — alongside an initial prototype showing how a Gemini-powered agent could connect those models to answer cross-modal questions.
Since then, we have evolved a Geospatial Reasoning agent from an early concept into a much more capable, experimental system built for multi-step, geospatial reasoning across planet-scale data and autonomous training of custom predictive models. Today, we are sharing three updates:
- A new technical report on geospatial reasoning: We present systematic evaluations across four benchmarks, including GeoKTools and GeoExpertQueries, two new benchmarks we developed and are releasing for researchers to test their own geospatial reasoning agents. Our results quantify the value of Earth AI’s specialized tools and planning over out-of-the-box LLMs.
- Insights from real-world partner testing: Over the past few months, we invited a small group of social impact and commercial partner organizations — including the World Health Organization (WHO) Regional Office for Africa, People in Need, GiveDirectly, the Milken Institute and WPP — to test the agent in support of their own real-world workflows, such as disease outbreak investigations, disaster preparedness, and clean energy screening.
- Expanding early access on Google Earth and Google Cloud: We are expanding experimental access for both multi-step geospatial analysis and for planetary prediction. We’re offering early access to an experimental deep research update for Ask Google Earth. We’re also providing early access to an agent-to-agent API for developers building custom workflows, including integration recipes for connecting to Gemini.
General-purpose LLMs and standard coding tools struggle with real-world spatial problems because planetary datasets are massive, with specialized map and satellite formats that require careful multi-step planning to combine accurately. To tackle complex spatial workflows in practice, our agent brings together four key capabilities:
The agent connects Gemini to the capabilities of Earth AI’s foundation models — including WeatherNext, Flood Forecasting, the Population Dynamics Foundation Model (PDFM), AlphaEarth Foundations and Remote Sensing Foundations — alongside information from Google Maps Platform (e.g., place information, routing, air quality, rooftop solar potential), Google Earth Engine, Data Commons and Google Dataset Search.
Earth AI capabilities are packaged as modular skills that the agent calls only when a user question needs them. Before running complex operations, the agent builds a step-by-step analytical plan, selects appropriate fallback datasets when local coverage is sparse, and processes large map layers in a dedicated workspace. This approach avoids overwhelming the agent context with massive amounts of spatial data, while preserving accuracy and tracking data attribution. Every response shows the agent’s plan and the data sources used so experts can check assumptions or substitute datasets.
Organizations rarely rely on public data alone. Users can now input their own datasets via the Geospatial Reasoning agent API as CSV spreadsheets, custom map boundaries (GeoJSON), or cloud tables. Users can then ask the agent to join their private locations with Earth AI’s global models and catalogs.
Beyond answering complex analytical questions, the agent also powers our recently announced Planetary Prediction Engine. Given a user’s local outcome data, such as regional disease rates, crop yields, or grid outages, the agent automatically selects relevant population and environmental signals, fuses our Population Dynamics Insights and Custom Satellite Embeddings (Google Maps Platform products built on PDFM and AlphaEarth Foundations, respectively) and trains validated machine learning models for spatial prediction, super-resolution downscaling, and forecasting. In our recent public health research, combining these population and satellite signals improved predictions of health outcomes by 12% over demographic baselines and enabled mapping at 8X finer spatial resolution.
To measure the impact of domain-specific tools and upfront planning on geospatial reasoning, our technical report compares four agent configurations across Gemini 3.8 Flash and Gemini 3.1 Pro: (1) a standalone LLM, (2) the LLM with basic web search and maps grounding tools, (3) the LLM with Earth AI tools (such as Remote Sensing Foundations and WeatherNext 3) but without upfront planning, and (4) the full Geospatial Reasoning agent which begins every query with a dedicated planning stage that reasons over available capabilities to assess what it can and cannot do and sets out the stages of retrieval and processing needed to reach an answer.
The evaluation spans four benchmarks, covering expert-level open-ended analysis, multi-tool orchestration, and community-developed geospatial problems with deterministic answers. CBGB and UnivEARTH are two externally developed benchmarks that test geospatial code generation and question answering respectively. To test agents on challenging tasks that go beyond a single question or use case, we developed two new benchmarks. GeoExpertQueries introduces complex, real-world queries with expert-authored golden workflows that capture analysis best practices in domains like crisis resilience, site selection and public health. GeoKTools contains templated queries with verifiable answers, each requiring correct selection and use of 1 to 4 distinct geospatial tools. Together, this suite provides substantially broader coverage than prior evaluations of geospatial reasoning systems. To accelerate research and development of geospatial agents, we release the development splits of both our new benchmarks in full.
Two key takeaways stand out from our evaluation: First, domain-specific skills are essential for spatial reasoning. The agent with only basic tools (web search, maps grounding and code execution) struggles on quantitative spatial tasks. Equipping the agent with Earth AI skills drives a significant jump across GeoExpertQueries, GeoKTools, and CBGB. The only exception is UnivEARTH, where even a standalone LLM scores 93.6%, likely because the source NASA articles and answers are available on the public web.
Second, upfront planning unlocks open-ended, real-world workflows. While Earth AI skills alone are enough for narrower tasks like those in CBGB and GeoKTools, tackling open-ended problems in GeoExpertQueries requires upfront planning to keep the agent on track across multi-step analyses and prevent it from making unreliable assumptions or taking shortcuts like using web-search instead of spatial tools.
The table below shows scores across all four benchmarks using Gemini 3.8 Flash:
The technical report also discusses limitations. GeoExpertQueries scores come from an autorater that compares the agent’s performance to expert workflows that define the steps an analysis should take, not the correct final answer. We therefore consider the agent’s output as a strong first draft for experts to review and build on, not a final answer.
To evaluate how this research translates to real-world challenges, we gave a small group of partners early access to test the experimental agent on their toughest problems. Across public health, disaster response, and infrastructure planning, below is an overview of how they are putting Earth AI into action:
- World Health Organization (WHO AFRO) & DRC’s INRB: At the start of the 2026 Ebola outbreak in the Democratic Republic of the Congo (DRC), WHO AFRO’s Emergency Preparedness and Response Hub in Dakar used the Geospatial Reasoning agent to map remote mining corridors where the exposure risk and human mobility are high by cross-referencing forest loss (from satellite images), mining sites (from maps and web data), and population data. In minutes, the team pinpointed 48 exposed settlements and located more than 45,500 at-risk people — a process that normally would have taken weeks. This allowed local responders to proactively deploy mobile laboratories and coordinate border surveillance. Meanwhile, the Epidemic Modeling and Intelligence Unit (UMIE) at the DRC’s National Institute for Biomedical Research (INRB) used the Planetary Prediction Engine to estimate the risk of Ebola spreading into uninfected zones. By combining mobility flows with historical case trends and Earth AI models and datasets, these weekly insights give coordinators critical planning time before cases arrive.
- “Mobile populations like miners move faster than traditional paper surveillance can track, creating dangerous blind spots. Earth AI fills those gaps with satellite and mobility signals—moving us from reactively chasing a virus to actively forecasting where it will strike next.” Dr Etien Koua, HIS Program Area Manager & Hub Coordinator for WHO AFRO Emergency Preparedness and Response (watch the video)
- People in Need: Geospatial reasoning helped combine natural disaster forecasts with population and imagery information, shifting analysts’ focus from data processing to providing insights:
- "The experimental Geospatial Reasoning agent helped us analyze 14 historical cyclone paths to identify high-exposure villages in minutes rather than days of manual GIS work, turning prepared complex data into immediate insights and freeing up critical time for life-saving anticipatory action." - Alonso Gonzales, GIS and Remote Sensing Coordinator
- GiveDirectly: Teams uploaded custom map boundaries to rapidly calculate population exposure by wind-speed zones during Tropical Cyclone Maila and benchmark tornado damage in Mississippi, cutting crisis scoping from days to minutes inside a single workspace.
- WPP: used geospatial reasoning to connect Population Dynamics Insights with their proprietary data. Their case study demonstrates how Earth AI insights enhanced the performance of geospatial marketing campaigns, while preserving the privacy of their data.
- Milken Institute: Pre-development teams used the agent to combine their own lists of 1,500+ candidate buildings with Google Maps Platform’s Solar API and census data in order to screen locations for building community resilience hubs, taking into account rooftop solar potential, mobility data, nearby transit hubs, climate risks, and federal investment zone eligibility.
Early testing with these partners helped our evaluation and expansion of the agent’s geospatial skills, driving our recent additions of road-network routing, support for larger user-uploaded datasets, and better discovery of authoritative local data sources.
Today, we are expanding access across our Earth AI research capabilities to gather more feedback on these experimental geospatial reasoning capabilities. We are making these available to a limited group of early users:
- Ask Google Earth: preview expanded deep analysis capabilities directly inside Ask Google Earth. This provides an interactive chat experience where you can ask complex spatial questions in natural language, analyze data — including your own — in Google Earth projects, and explore visual results directly on the map.
- Geospatial Reasoning Agent API: For developer teams that want a customizable, do-it-yourself integration to power custom workflows, we offer an experimental headless Agent-to-Agent(A2A) service. Early partners can connec
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.