A Multi-Level Validation and Traceability Framework for AI-Generated Telescope Scheduling Decisions

Abstract

With the gradual introduction of AI into telescope scheduling, AI-based decision-making has shown advantages in handling complex multi-constraint problems. However, its outputs often suffer from inconsistent data references, reasoning errors, and non-executable decisions, limiting applicability in high-reliability observational tasks. In this work, we propose a multi-level validation and traceable reasoning framework that performs systematic reliability verification of AI-generated decisions prior to execution, and enables explicit representation of the reasoning process to support traceable decision-making. The framework integrates data reference validation, logical consistency checks, and observational and instrumental constraint verification to filter and correct invalid decisions. It also introduces atomic reasoning units and their dependency relationships, representing scheduling decisions as a sequence of interconnected reasoning steps that support error localization and post hoc analysis. Experiments show that the framework improves executability and reliability of AI scheduling and reduces loss of transient opportunities. In particular, feedback correction and structured validation of reasoning steps enhance the ability to repair and block erroneous decisions, especially in complex scenarios. Compared with pure AI methods, the framework-enhanced approach maintains flexibility while substantially improving reliability and executability. These results demonstrate a feasible and verifiable pathway for applying AI to high-reliability astronomical observation scheduling.

25 pages, 8 figures, Published in Universe

References in corpus (11)

• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Pan-STARRS Data Processing System
• The Zwicky Transient Facility Alert Distribution System
• A Framework for Telescope Schedulers: With Applications to the Large Synoptic Survey Telescope
• A Multilevel Scheduling Framework for Distributed Time-domain Large-area Sky Survey Telescope Array
• The indiscriminate adoption of AI threatens the foundations of academia
• The Mini-SiTian Array: Optical design
• AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model
• GRRIS: a real-time intra-site observation scheduling scheme for distributed survey telescope arrays
• The automation of optical transient discovery and classification in Rubin-era time-domain astronomy