{"ID":2880413,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15066","arxiv_id":"2508.15066","title":"Osprey: Production-Ready Agentic AI for Safety-Critical Control Systems","abstract":"Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface for these tasks, but most existing approaches are not yet reliable or safe enough for production use. In this paper, we introduce Osprey, a framework for using agentic AI in large, safety-critical facility operations. Osprey is built around the needs of control rooms and addresses these challenges in four ways. First, it uses a plan-first orchestrator that generates complete execution plans, including all dependencies, for human review before any hardware is touched. Second, a coordination layer manages complex data flows, keeps data types consistent, and automatically downsamples large datasets when needed. Third, a classifier dynamically selects only the tools required for a given task, keeping prompts compact as facilities add capabilities. Fourth, connector abstractions and deployment patterns work across different control systems and are ready for day-to-day use. We demonstrate the framework through two case studies: a control-assistant tutorial showing semantic channel mapping and historical data integration, and a production deployment at the Advanced Light Source, where Osprey manages real-time operations across hundreds of thousands of control channels. These results establish Osprey as a production-ready framework for deploying agentic AI in complex, safety-critical environments.","short_abstract":"Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface for these tasks, but most existing approaches are not yet reliable or safe enou...","url_abs":"https://arxiv.org/abs/2508.15066","url_pdf":"https://arxiv.org/pdf/2508.15066v3","authors":"[\"Thorsten Hellert\",\"João Montenegro\",\"Antonin Sulc\"]","published":"2025-08-20T20:57:13Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.IR\"]","methods":"[\"Language Model\"]","has_code":false}