mlsanityData to 13 Oct 2026

EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models

arXiv 2602.17419 ↗First posted 19 Feb 2026cs.CVcited by 2

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

Multimodal large language models (MLLMs) can enrich industrial anomaly detection with semantic descriptions and anomaly reasoning, but they still lag specialist anomaly detectors in binary detection accuracy. Existing approaches address this gap by fine-tuning MLLMs or training bridging modules to align expert outputs with MLLM inputs, limiting flexibility across backbones. We propose EAGLE, a tuning-free framework that integrates expert anomaly detectors with frozen MLLMs. EAGLE consists of Threshold-Guided Prompt Selection (TGPS), which estimates a decision threshold from expert model statistics and selects textual and visual prompts, and Confidence-Aware Attention Sharpening (CAAS), which shifts MLLM attention toward visual evidence when expert confidence is low. Beyond improving accuracy, we analyze MLLM attention and find that correct anomaly predictions are associated with stronger focus on ground-truth defect regions; EAGLE consistently strengthens this alignment. On MVTec-AD and VisA, EAGLE improves five MLLM backbones without parameter updates, reaching up to 94.4% and 88.1% in anomaly discrimination accuracy, respectively, and achieving performance competitive with fine-tuning-based methods while largely preserving MLLM semantic reasoning ability.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 44 of its 52 references that are in the map. First posted on arXiv 19 Feb 2026.

Builds on

44 of 52 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models5 May
  2. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models11 Feb
  3. 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?27 Jan
  4. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection12 Oct
  5. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection29 Oct
  6. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models29 Aug

Other references · 38

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  2. 2025Qwen2.5-VL Technical Reportcited by 5,499
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,389
  4. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,506
  5. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,798
  6. 2019Towards VQA Models That Can Readcited by 1,705
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 774
  8. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 723
  9. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 708
  10. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 677
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 511
  12. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 399
26 more
  1. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  2. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 314
  3. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  4. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  5. 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMscited by 173
  6. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 158
  7. 2025See What You Are Told: Visual Attention Sink in Large Multimodal Modelscited by 127
  8. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  9. 2025Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areascited by 94
  10. 2024MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationcited by 87
  11. 2024Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attentioncited by 74
  12. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  13. 2024Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Modelscited by 47
  14. 2025ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Modelscited by 40
  15. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  16. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extractioncited by 24
  17. 2024LogiCode: an LLM-Driven Framework for Logical Anomaly Detectioncited by 18
  18. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  19. 2025IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detectioncited by 17
  20. 2024FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queriescited by 12
  21. 2025EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Modelscited by 11
  22. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 11
  23. 2025LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoningcited by 9
  24. 2024RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detectioncited by 8
  25. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8
  26. 2024Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interferencecited by 7

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutationcited by 0
  2. 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. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  2. 2025IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection
  3. 2026A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
  4. 2025SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment
  5. 2026IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
  6. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
  7. 2026Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection
  8. 2026M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection