[Submitted on 13 May 2026 (v1), last revised 21 Oct 2026 (this version, v3)]
Abstract:The Industry Foundation Classes (IFC) standard is central to building data exchange across the lifecycle, from design and construction to facility management and Digital Twin integration. In operational settings, stakeholders increasingly require access to building information without specialist knowledge of IFC’s complex, deeply nested schema, motivating natural language interfaces. Existing Large Language Model (LLM)-based querying approaches typically rely on a single data representation, which is not equally suited to attribute retrieval and spatial reasoning. We present IfcLLM, a framework that combines complementary relational and graph representations, routing each query type to the more suitable backend. An LLM agent integrates both through iterative retry-and-refine reasoning, recovering from failures without user input. Evaluated on 30 query scenarios across three IFC models, the top-performing configuration achieved 96% accuracy. Results with open-weight LLMs further demonstrate the potential for local deployment in data-sensitive AEC settings.
Submission history
From: Rabindra Lamsal [view email]
[v1] Wed, 13 May 2026 09:24:51 UTC (4,096 KB)
[v2] Mon, 22 Jun 2026 02:54:53 UTC (3,931 KB)
[v3] Wed, 21 Oct 2026 23:25:08 UTC (4,381 KB)
