GeoDisaster: 用于操作化灾害地理智能的编排智能体基准测试
GeoDisaster: Benchmarking Orchestrated Agents for Operational Disaster Geo-Intelligence
AI总结：
提出GeoDisaster基准，包含2921个实例和43种问题类型，用于评估遥感视觉语言模型在工具化空间推理和结构化决策方面的能力，并设计多智能体框架RCEA提升工具使用和证据基础。
摘要：
遥感视觉语言模型（RS-VLMs）推动了地球观测分析向视觉解释和指令遵循发展，但在操作化地理智能方面仍显不足，后者需要基于工具的空间推理和结构化、有证据支持的决策。我们提出了GeoDisaster，一个操作化地理空间灾害推理基准，包含2921个经过验证的实例，涵盖43种问题类型和五个任务族：森林砍伐监测、多灾害分析、建筑损坏评估、洪水安全路线规划以及Sentinel-1 SAR洪水监测。实例集成了异构的EO/GIS证据——光学和SAR影像、栅格掩膜、矢量几何、道路网络和暴露图层——涵盖灾害检测、损坏评估、暴露估计和诊断报告生成。真实答案基于可执行的地理空间工作流和确定性一致性检查，无需语言模型标注。我们进一步提出了一个编排的多智能体框架，包含18个面向灾害的工具，其中角色专业化的智能体通过明确的执行契约进行协调，并通过角色契约期望对齐（RCEA）进行对齐：结合故障感知的监督微调和基于契约的强化学习，利用密集的步骤级信号。实验表明，GeoDisaster对现有的RS-VLMs和智能体系统构成了挑战，而RCEA改进了工具使用、证据基础、状态一致性和决策生成。
英文摘要：
Remote-sensing vision-language models (RS-VLMs) have advanced Earth-observation analysis toward visual interpretation and instruction-following, yet fall short of operational geo-intelligence, which demands tool-grounded spatial reasoning and structured, evidence-backed decisions. We introduce GeoDisaster, an operational geospatial disaster reasoning benchmark with 2,921 verified instances across 43 question types and five task families: deforestation monitoring, multi-hazard analysis, building-damage assessment, flood-safe routing, and Sentinel-1 SAR flood monitoring. Instances integrate heterogeneous EO/GIS evidence-optical and SAR imagery, raster masks, vector geometries, road networks, and exposure layers-spanning hazard detection, damage assessment, exposure estimation, and diagnostic report generation. Ground-truth answers are grounded in executable geospatial workflows and deterministic consistency checks, removing the need for language-model annotation. We further propose an orchestrated multi-agent framework with 18 disaster-oriented tools, where role-specialized agents coordinate through explicit execution contracts, aligned via Role-Contract Expectation Alignment (RCEA): failure-aware supervised fine-tuning combined with contract-grounded reinforcement learning over dense step-level signals. Experiments show that GeoDisaster challenges existing RS-VLMs and agentic systems, while RCEA improves tool use, evidence grounding, state consistency, and decision generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
