Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection
2026-06-03 • Artificial Intelligence
Artificial IntelligenceComputational Engineering, Finance, and Science
AI summaryⓘ
The authors study how to use large language models (LLMs) to help detect problems in industrial manufacturing. They noticed existing systems mostly focus on doing tasks but not planning well, which makes it hard to handle different types of data efficiently. They created DMAIC-IAD, a system that first plans by turning diverse information into clear steps before deciding on a strategy, using a special model to judge plans without expensive tests. Their experiments show this method improves detection performance significantly compared to other similar approaches.
Large Language ModelsIndustrial Anomaly DetectionDMAIC FrameworkMulti-Agent SystemsStandard Operating ProceduresStrategy FormulationQuality ManagementExecution-Free Judge ModelHeterogeneous ModalitiesManufacturing Quality
Authors
Yongzi Yu, Ao Li, Le Wang, Ziyue Li, Fugee Tsung, Yuxuan Liang, Man Li
Abstract
Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in high-stakes industrial scenarios. Industrial anomaly detection (IAD) is essential for manufacturing quality, safety, and efficiency, yet existing LLM-based IAD agents mainly focus on execution while under-exploiting strategy formulation. Consequently, they struggle to handle heterogeneous modalities in a unified and cost-effective manner. Inspired by the DMAIC quality-management framework, we propose DMAIC-IAD (DMAIC-inspired Agentic Industrial Anomaly Detection), a "Plan First, Judge Later" multi-agent system that aligns LLM agents with structured industrial problem-solving. DMAIC-IAD distills heterogeneous references into standardized operating procedures (SOPs) before strategy generation, and introduces a pre-trained execution-free judge model to rank candidate strategies without costly runtime trials. Extensive experiments across four modalities show that DMAIC-IAD improves average detection performance over applicable agentic baselines by 37.76%.