AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis

2026-04-17

AI Summary

Astronomical image quality diagnosis faces significant challenges due to the complexity of the imaging process, its inherently interdisciplinary nature, and the strong coupling among subtasks. This work proposes the first vision-language model system based on multi-agent collaborative reasoning, integrating domain expert knowledge into a multi-agent cooperative architecture to enable automatic diagnosis and precise localization of image quality issues. By deeply fusing multi-agent reasoning with vision-language models, the method effectively addresses the coupling inherent in complex, multi-stage tasks. Evaluated on real astronomical image data, the approach substantially outperforms existing baselines, offering a novel paradigm for tackling high-dimensional, complex procedural tasks in scientific domains.

Technology Category

• Computer Vision: Multi-modal Vision
• Multiagent Systems: Teamwork
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Vision Language Models (VLMs) have been applied to several specific domains and have shown strong problem-solving capabilities. However, astronomical imaging, a quite complex problem involving multidisciplinary knowledge and several subtasks, has not been adequately studied. Due to the complexity of the astronomical imaging process, both world-class astronomical organizations, such as NASA, and expert enthusiasts devote a great deal of time and effort. This is because the processes in astronomical imaging have complex underlying correlations that significantly influence one another, making the quality diagnosis and error localization of astronomical images challenging. To address this problem, we propose AstroVLM, a collaborative multi-agent system for diagnosing the quality of astronomical images. Experiment results show that AstroVLM outperforms all baselines on real-world astronomical imaging quality diagnosis tasks, providing a reference for language models to handle complicated multi-process tasks.

Problem

• astronomical imaging
• quality diagnosis
• error localization
• multi-agent reasoning
• vision language models

Innovation

• Multi-agent Collaboration
• Astronomical Imaging
• Vision Language Models
• Quality Diagnosis
• Expert Reasoning