mlsanityData to 14 Oct 2026

AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection

arXiv 2504.11914 ↗First posted 16 Apr 2025cs.CVcited by 28

On the map: LLM reasoning → Chain-of-thought reasoning for driving

Abstract (arXiv)

Industrial Anomaly Detection (IAD) poses a formidable challenge due to the scarcity of defective samples, making it imperative to deploy models capable of robust generalization to detect unseen anomalies effectively. Traditional approaches, often constrained by hand-crafted features or domain-specific expert models, struggle to address this limitation, underscoring the need for a paradigm shift. We introduce AnomalyR1, a pioneering framework that leverages VLM-R1, a Multimodal Large Language Model (MLLM) renowned for its exceptional generalization and interpretability, to revolutionize IAD. By integrating MLLM with Group Relative Policy Optimization (GRPO), enhanced by our novel Reasoned Outcome Alignment Metric (ROAM), AnomalyR1 achieves a fully end-to-end solution that autonomously processes inputs of image and domain knowledge, reasons through analysis, and generates precise anomaly localizations and masks. Based on the latest multimodal IAD benchmark, our compact 3-billion-parameter model outperforms existing methods, establishing state-of-the-art results. As MLLM capabilities continue to advance, this study is the first to deliver an end-to-end VLM-based IAD solution that demonstrates the transformative potential of ROAM-enhanced GRPO, positioning our framework as a forward-looking cornerstone for next-generation intelligent anomaly detection systems in industrial applications with limited defective data.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning. Builds on 26 of its 63 references that are in the map. First posted on arXiv 16 Apr 2025.

Builds on

26 of 63 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models11 Feb

Other references · 25

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2023Qwen Technical Reportcited by 3,344
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  7. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  8. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  9. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  10. 2024LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Modelscited by 584
  11. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
13 more
  1. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 286
  2. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  3. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  4. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  5. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  6. 2023Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuningcited by 58
  7. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  8. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extractioncited by 25
  9. 2024Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoningcited by 20
  10. 2021A Few More Examples May Be Worth Billions of Parameterscited by 19
  11. 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?cited by 17
  12. 2025EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Modelscited by 11
  13. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 21.

28 papers.

Sort:

By area:

  1. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  2. 2025IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detectioncited by 17
  3. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 12
  4. 2025LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoningcited by 9
  5. 2026Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoningcited by 6
  6. 2025AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentationcited by 4
  7. 2026JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QAcited by 4
  8. 2026Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervisioncited by 3
  9. 2026EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Modelscited by 2
  10. 2026IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Toolscited by 2
  11. 2025ABounD: Adversarial Boundary-Driven Few-Shot Learning for Multi-Class Anomaly Detectioncited by 1
  12. 2026UniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspectioncited by 1
16 more
  1. 2026M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detectioncited by 1
  2. 2026Topo-R1: Detecting Topological Anomalies via Vision-Language Modelscited by 1
  3. 2026AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detectioncited by 1
  4. 2026CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detectioncited by 1
  5. 2026OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillationcited by 1
  6. 2025Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimizationcited by 0
  7. 2026GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detectioncited by 0
  8. 2026MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detectioncited by 0
  9. 2026DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Modelscited by 0
  10. 2026From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Modelscited by 0
  11. 2026Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detectioncited by 0
  12. 2026ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detectioncited by 0
  13. 2026Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraintcited by 0
  14. 2026Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Spacecited by 0
  15. 2026TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localizationcited by 0
  16. 2026Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
  2. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
  3. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  4. 2025Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
  5. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
  6. 2025IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection
  7. 2026MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models
  8. 2025A Survey on Industrial Anomaly Synthesis