AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
also in 2 more
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 12 of its 46 references that are in the map. First posted on arXiv 17 Apr 2026.
Builds on
12 of 46 references.
References · 12
- 2024GPT-4o System Cardcited by 4,588
- 2025Qwen3-VL Technical Reportcited by 2,793
- 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
- 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 572
- 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
- 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
- 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 159
- 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
- 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 61
- 2025Evaluating Vision-Language Models for Emotion Recognitioncited by 19
- 2025Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automationcited by 12
- 2024Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoningcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026A systematic evaluation of vision-language models for observational astronomical reasoning tasks
- 2026Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection
- 2025Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilities
- 2025AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
- 2026Reconstructing Implicit Scientific Knowledge: Evaluating LLM Agents through End-to-End Reproduction of Astronomy
- 2025AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model
- 2025AstroReview: An LLM-driven Multi-Agent Framework for Telescope Proposal Peer Review and Refinement
- 2026AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification