让大模型具备地理感知能力，提升火灾响应决策的准确性与可解释性。
Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response
- 通过地学数据层将地理信息注入大模型，实现空间上下文理解。
- 在真实火情中，决策准确率显著优于传统文本模型。
- 适用于火灾、洪水等多类灾害，适合应急决策系统研发者使用。
有效灾害响应对保护生命财产至关重要。现有统计方法常缺乏语义上下文，跨事件泛化能力差，且可解释性有限。尽管大语言模型（LLMs）具备少样本泛化能力，但仍局限于文本，无法感知地理空间。为此，我们提出地学感知层（Geospatial Awareness Layer, GAL），将LLM代理与结构化地球数据结合。从原始野火探测数据出发，GAL自动从外部地理数据库检索并整合基础设施、人口分布、地形和天气信息，生成带单位标注的紧凑感知脚本。该增强上下文使代理能生成基于证据的资源分配建议（如人员派遣、预算分配），并通过历史相似案例与每日变化信号实现持续更新。我们在多个真实野火场景下评估了该框架在不同LLM模型上的表现，结果表明地学感知代理优于基线模型。该框架还可推广至洪水、飓风等其他灾害场景。
原文摘要 · Abstract (English)
Effective disaster response is essential for safeguarding lives and property. Existing statistical approaches often lack semantic context, generalize poorly across events, and offer limited interpretability. While Large language models (LLMs) provide few-shot generalization, they remain text-bound and blind to geography. To bridge this gap, we introduce a Geospatial Awareness Layer (GAL) that grounds LLM agents in structured earth data. Starting from raw wildfire detections, GAL automatically retrieves and integrates infrastructure, demographic, terrain, and weather information from external geodatabases, assembling them into a concise, unit-annotated perception script. This enriched context enables agents to produce evidence-based resource-allocation recommendations (e.g., personnel assignments, budget allocations), further reinforced by historical analogs and daily change signals for incremental updates. We evaluate the framework in real wildfire scenarios across multiple LLM models, showing that geospatially grounded agents can outperform baselines. The proposed framework can generalize to other hazards such as floods and hurricanes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。