# LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection

arXiv: https://arxiv.org/abs/2504.12749 · HTML: https://mlsanity.com/paper/2504.12749/

## Key facts

- Cited by 9 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 25 of its 42 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)

## Builds on (most cited first, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD](https://mlsanity.com/paper/2305.17382/) (2023)
- [MM-RLHF: The Next Step Forward in Multimodal LLM Alignment](https://mlsanity.com/paper/2502.10391/) (2025)
- [Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2502.07601/) (2025)
- [Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection](https://mlsanity.com/paper/2310.19070/) (2023)
- [Towards Training-free Anomaly Detection with Vision and Language Foundation Models](https://mlsanity.com/paper/2503.18325/) (2025)
- [LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction](https://mlsanity.com/paper/2501.01767/) (2025)
- [CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection](https://mlsanity.com/paper/2408.15628/) (2024)
- [Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning](https://mlsanity.com/paper/2411.17217/) (2024)
- [Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection](https://mlsanity.com/paper/2502.11712/) (2025)

## Built on by (most cited first, 9 of 9)

- [OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning](https://mlsanity.com/paper/2505.22039/) (2025)
- [IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection](https://mlsanity.com/paper/2508.09178/) (2025)
- [EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO](https://mlsanity.com/paper/2507.21619/) (2025)
- [LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoning](https://mlsanity.com/paper/2504.19524/) (2025)
- [AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation](https://mlsanity.com/paper/2512.13671/) (2025)
- [TAU-R1: Visual Language Model for Traffic Anomaly Understanding](https://mlsanity.com/paper/2603.19098/) (2026)
- [Multimodal Industrial Anomaly Detection via Geometric Prior](https://mlsanity.com/paper/2603.22757/) (2026)
- [From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models](https://mlsanity.com/paper/2606.26196/) (2026)
- [Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection](https://mlsanity.com/paper/2607.03817/) (2026)

## Abstract (arXiv)

Recent advances in industrial anomaly detection have highlighted the need for deeper logical anomaly analysis, where unexpected relationships among objects, counts, and spatial configurations must be identified and explained. Existing approaches often rely on large-scale external reasoning modules or elaborate pipeline designs, hindering practical deployment and interpretability. To address these limitations, we introduce a new task, Reasoning Logical Anomaly Detection (RLAD), which extends traditional anomaly detection by incorporating logical reasoning. We propose a new framework, LAD-Reasoner, a customized tiny multimodal language model built on Qwen2.5-VL 3B. Our approach leverages a two-stage training paradigm that first employs Supervised Fine-Tuning (SFT) for fine-grained visual understanding, followed by Group Relative Policy Optimization (GRPO) to refine logical anomaly detection and enforce coherent, human-readable reasoning. Crucially, reward signals are derived from both the detection accuracy and the structural quality of the outputs, obviating the need for building chain of thought (CoT) reasoning data. Experiments on the MVTec LOCO AD dataset show that LAD-Reasoner, though significantly smaller, matches the performance of Qwen2.5-VL-72B in accuracy and F1 score, and further excels in producing concise and interpretable rationales. This unified design reduces reliance on large models and complex pipelines, while offering transparent and interpretable insights into logical anomaly detection. Code and data will be released.