A Role-Specialized Retrieval-Augmented Generation Framework for Automated Compliance Checking in Structural Engineering

Abstract

Automated code compliance checking in structural engineering remains difficult because practical systems must balance accuracy, maintainability, and deployment cost. Pure prompting with large language models is prone to hallucination and unstable numerical judgment, conventional retrieval-augmented generation may fail to assemble dispersed regulatory evidence, and ontology-heavy pipelines can be expensive to extend when codes evolve. We therefore propose a role-specialized retrieval-augmented generation framework composed of a deterministic Parser, a Reviewer guided by an Equilibrium Rule prompt, and a Critic that outputs a structured verdict. On a 211-case benchmark built from real-project building information modeling exports and expert review across slabs, beams, and columns, the framework achieves 96.68% overall accuracy, compared with 57.35% for zero-shot prompting, 79.15% for naive retrieval-augmented generation, 77.25% for naive retrieval-augmented generation with the Equilibrium Rule, and 89.10% for a re-implemented ontology- and rule-based baseline. The benchmark knowledge resources, retrieval corpus, and rule-supporting mappings are extracted from two Chinese national structural design codes covering concrete member design and structural loading. Ablation results suggest that the Equilibrium Rule and the Critic contribute most of the observed gain. We therefore position the framework as a decision-support approach for engineering compliance review rather than as a fully autonomous approval engine.