[Submitted on 10 Feb 2026 (v1), last revised 21 Oct 2026 (this version, v3)]
Abstract:Industrial anomaly detection demands precise reasoning over fine-grained defect patterns. However, existing multimodal large language models (MLLMs), pretrained on general-domain data, often struggle to capture category-specific anomalies, thereby limiting both detection accuracy and interpretability. To address these limitations, we propose Reason-IAD, a knowledge-guided dynamic latent reasoning framework for explainable industrial anomaly detection. Reason-IAD comprises two core components. First, a retrieval-augmented knowledge module incorporates category-specific textual descriptions into the model input, enabling context-aware reasoning over domain-specific defects. Second, an entropy-driven latent reasoning mechanism conducts iterative exploration within a compact latent space using optimizable latent think tokens, guided by an entropy-based reward that encourages confident and stable predictions. Furthermore, a dynamic visual injection strategy selectively incorporates the most informative image patches into the latent sequence, directing the reasoning process toward regions critical for anomaly detection. Extensive experimental results demonstrate that Reason-IAD consistently outperforms state-of-the-art methods across multiple tasks. The code will be publicly available at this https URL.
Submission history
From: Peng Chen [view email]
[v1] Tue, 10 Feb 2026 14:54:17 UTC (1,484 KB)
[v2] Fri, 8 May 2026 01:43:02 UTC (1,519 KB)
[v3] Wed, 21 Oct 2026 14:07:12 UTC (1,519 KB)
