Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation
For users of geospatial data retrieval systems, this work addresses the need for safe and reliable natural language interfaces to cloud-based catalogues, though it is an incremental design with preliminary evaluation.
The paper presents an LLM-driven framework for retrieving remote sensing data from geospatial catalogues using natural language, integrating three agents for safety, intent interpretation, and API call generation. Preliminary adversarial evaluation shows prompt-level safety instructions improve robustness but rare high-impact failures persist, motivating system-level defenses.
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.