Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation
Quick Answer
The proposed LLM-driven framework efficiently retrieves remote sensing data via natural language queries, integrating Guardrail, General-QA, and Recommender-Analyst agents for robust API interactions.
Quick Take
Preliminary adversarial evaluations indicate that safety instructions enhance system resilience, though high-impact failures in API manipulation highlight the need for adaptive defenses.
Key Points
- Framework converts user intent into structured API calls for satellite imagery access.
- Integrates three agents: Guardrail, General-QA, and Recommender-Analyst for enhanced safety.
- Supports applications in environmental monitoring, disaster response, and climate analysis.
- Preliminary tests show prompt-level safety instructions improve robustness against adversarial queries.
- High-impact failures in API manipulation indicate a need for adaptive system-level defenses.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 15077v1 Announce Type: new Abstract: We present an -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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.