SOPRAG: Multi-view Graph Experts Retrieval for Industrial Standard Operating Procedures
This addresses the challenge of retrieving and following SOPs for industrial operators, with incremental improvements in domain-specific retrieval methods.
The paper tackled the problem of retrieving Standard Operating Procedures (SOPs) in industrial environments, which standard RAG methods fail to address due to structural and logical complexities, and proposed SOPRAG, a multi-view graph experts framework that achieved perfect execution scores in real-world critical tasks and outperformed baselines in retrieval accuracy and response utility.
Standard Operating Procedures (SOPs) are essential for ensuring operational safety and consistency in industrial environments. However, retrieving and following these procedures presents unique challenges, such as rigid proprietary structures, condition-dependent relevance, and actionable execution requirement, which standard semantic-driven Retrieval-Augmented Generation (RAG) paradigms fail to address. Inspired by the Mixture-of-Experts (MoE) paradigm, we propose SOPRAG, a novel framework specifically designed to address the above pain points in SOP retrieval. SOPRAG replaces flat chunking with specialized Entity, Causal, and Flow graph experts to resolve industrial structural and logical complexities. To optimize and coordinate these experts, we propose a Procedure Card layer that prunes the search space to eliminate computational noise, and an LLM-Guided gating mechanism that dynamically weights these experts to align retrieval with operator intent. To address the scarcity of domain-specific data, we also introduce an automated, multi-agent workflow for benchmark construction. Extensive experiments across four industrial domains demonstrate that SOPRAG significantly outperforms strong lexical, dense, and graph-based RAG baselines in both retrieval accuracy and response utility, achieving perfect execution scores in real-world critical tasks.