{"slug": "risk-aware-llm-agents-for-geospatial-data-retrieval-design-and-preliminary", "title": "Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation", "summary": "Researchers introduced an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system uses three agents—Guardrail, General-QA, and Recommender-Analyst—to convert user intent into structured API calls. Preliminary adversarial tests show prompt-level safety instructions improve robustness, but rare high-impact failures persist, motivating adaptive system-level defenses.", "body_md": "arXiv:2606.15077v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/risk-aware-llm-agents-for-geospatial-data-retrieval-design-and-preliminary", "canonical_source": "https://arxiv.org/abs/2606.15077", "published_at": "2026-06-16 04:00:00+00:00", "updated_at": "2026-06-16 04:20:57.585491+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-safety", "computer-vision", "natural-language-processing"], "entities": ["arXiv", "Guardrail", "General-QA", "Recommender-Analyst"], "alternates": {"html": "https://wpnews.pro/news/risk-aware-llm-agents-for-geospatial-data-retrieval-design-and-preliminary", "markdown": "https://wpnews.pro/news/risk-aware-llm-agents-for-geospatial-data-retrieval-design-and-preliminary.md", "text": "https://wpnews.pro/news/risk-aware-llm-agents-for-geospatial-data-retrieval-design-and-preliminary.txt", "jsonld": "https://wpnews.pro/news/risk-aware-llm-agents-for-geospatial-data-retrieval-design-and-preliminary.jsonld"}}