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
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.
BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction
BiNSGPS is a framework that introduces bidirectional interaction between a multimodal LLM adviser and a symbolic solver for geometry problem solving, allowing feedback from the solver to correct errors and generate auxiliary hypotheses. It achieves state-of-the-art performance of 90.5% on Geometry3K and 90.1% on PGPS9K benchmarks.
Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling
This paper introduces SIGMA, a signed graph-informed multi-agent reasoning framework that explicitly models trust, conflict, and neutral relations among LLM agents to achieve conflict-resilient and globally consistent predictions, outperforming state-of-the-art baselines on six benchmarks.
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
This paper proposes a self-supervised reinforcement learning framework that uses consistency verifiers—reward functions checking geometric and semantic consistency under transformations—to improve spatial reasoning in large reasoning models without requiring ground-truth annotations. The method approaches the accuracy of supervised fine-tuning and generalizes across diverse tasks.
Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval
This paper presents a system that automatically discovers an executable schema from raw multi-source data and uses it for knowledge graph construction and query-time retrieval, improving over baselines on QA benchmarks.