Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework
Summary
This paper introduces SGR-BIM, a graph-driven semantic reasoning framework that dynamically aligns regulatory intent with BIM geometry to automate geometry-intensive compliance checks, achieving 84.3% accuracy on fire safety code queries.
View Cached Full Text
Cached at: 06/11/26, 01:50 PM
# Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework Source: [https://arxiv.org/abs/2606.12065](https://arxiv.org/abs/2606.12065) [View PDF](https://arxiv.org/pdf/2606.12065) > Abstract:Automating compliance check for geometry\-intensive regulations remains a significant technical bottleneck in Building Information Modeling \(BIM\), primarily due to the semantic disparity between high\-level regulatory logic and structured IFC data\. Existing methods, often reliant on static rule templates, struggle to traverse multi\-hop reasoning chains or resolve latent spatial dependencies across multiple building entities\. To address these challenges, a Spatial\-Geometric Reasoning System for Building Information Modeling \(SGR\-BIM\) is proposed as an integrative graph\-driven reasoning framework\. SGR\-BIM dynamically constructs a cross\-modal knowledge graph that aligns user intent, regulatory semantics, and BIM geometry, enabling interpretable reasoning without rigid hard\-coding\. Validated on 679 expert\-verified queries from fire safety codes, the framework achieves 84\.3% accuracy, representing an 8\.6% improvement over enhanced\-tool single\-agent baselines\. This research provides a graph\-based semantic reasoning paradigm, enhancing the transparency and flexibility of automated geometric compliance check workflows in the Architecture, Engineering, and Construction \(AEC\) industry\. ## Submission history From: Zixuan Xiao \[[view email](https://arxiv.org/show-email/f75e9e73/2606.12065)\] **\[v1\]**Wed, 10 Jun 2026 13:31:43 UTC \(8,162 KB\)
Similar Articles
Intelligent Identification and Repair of Design Defects in BIM via Domain-Specific Large Language Models
This study proposes an integrated framework using domain-specific LLMs for intelligent identification and repair of design defects in BIM, achieving 85% accuracy and 94% reasonable repair suggestions with effective hallucination control.
Towards an automated AI-based framework for floor plan compliance checks for residential buildings
This paper proposes a conceptual AI-based framework for automated compliance checking of building floor plans using Large Language Models and computer vision to convert building codes into executable rules and evaluate structured building graphs.
SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation
Introduces SGR, a stepwise reasoning framework that enhances LLM reasoning by generating query-specific subgraphs from external knowledge bases, improving accuracy and factual reliability.
Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts
This paper introduces a neuro-symbolic pipeline for automating LEED v4.1 BD+C compliance verification using small locally deployed language models and deterministic numeric checking. Experiments on four university buildings show that a 4B model outperforms an 8B model, and the deterministic checker corrects arithmetic errors on key credits, though multimodal inputs reduce accuracy.
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling
BIM-Edit is a benchmark for evaluating LLMs on natural-language editing of Building Information Models (BIM) in IFC format. Results show a substantial gap, with the best model achieving only 49.5% average score across geometric, semantic, and topological metrics.