用大模型安全地从云端获取遥感数据，提升环境监测效率
Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation
- 三类智能体协同：理解意图、生成查询、保障安全
- 对抗测试中提示安全指令可提升鲁棒性，但仍有高风险漏洞
- 适合遥感应用开发、灾害响应与气候分析人员使用
我们提出一种基于大模型的框架，通过自然语言查询从云端地理空间目录中检索遥感数据。系统将用户意图转化为结构化API调用，实现对卫星影像与环境数据集的高效访问。架构包含三个智能体：Guardrail负责安全与策略执行，General-QA用于意图理解，Recommender-Analyst实现基于模式的API生成。该协同设计确保与外部数据服务的可靠语义交互。模块化结构支持跨平台迁移，通过替换API模式实现兼容性，适用于环境监测、灾害响应和气候分析。建立用户意图与地理空间基础设施间的可扩展接口，推动地球观测工作流自动化。初步对抗性多轮测试表明，提示层安全指令能增强系统鲁棒性，但API操作场景中仍存在罕见高影响失败，凸显需部署自适应、系统级防御机制，平衡安全、可用性与成本效率，由此驱动了拦截层Guardrail智能体的应用。
原文摘要 · Abstract (English)
We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system converts user intent into structured API calls, enabling efficient access to satellite imagery and environmental datasets. The architecture integrates three agents: Guardrail for safety and policy enforcement, General-QA for intent interpretation, and Recommender-Analyst for schema-aware API call generation. This coordinated design ensures reliable, semantically aligned interaction with external data services. The modular framework is portable across platforms through API schema substitution and supports applications in environmental monitoring, disaster response, and climate analysis. It establishes a scalable interface between user intent and geospatial infrastructure, enabling streamlined and automated Earth observation workflows. Preliminary experiments under adversarial multi-turn settings show that prompt-level safety instructions improve robustness, although rare high-impact failures persist in API manipulation scenarios and highlight the need for adaptive, system-level defenses that balance safety, usability, and cost efficiency, which motivates the use of our intercept-level Guardrail agent.
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。