BIM and semantic graphs are increasingly used in the AEC industry. Converting indoor point clouds into standards-compliant IFC BIM and graph representations remains non-trivial and often requires expert knowledge and manual post-processing steps. To address this, an LLM-enabled multi-agent framework is proposed to automate Scan-to-BIM and Scan-to-Graph from point clouds, with support for natural-language, intent-driven reconstruction. The framework integrates query interpretation, point-cloud inference, topology-aware IFC generation, semantic graph construction, and multi-stage validation into a single end-to-end pipeline, explicitly handling of wall–wall junctions and wall–slab alignment. The framework is evaluated on three datasets captured with different sensing modalities (mobile laser scanning, RGB-D, and synthetic). On the TUMCMS test set, a laser-scanned point cloud dataset captured in office environments at the Technical University of Munich, room areas of generated IFC files achieve mean absolute deviations of 1 . 45 m 2 (Llama-based) and 1 . 51 m 2 (Qwen-based), corresponding to mean relative deviations of 4.70% and 5.10% versus manually created BIM. The results demonstrate robust and generalized performance of the framework for wall and space reconstruction across datasets. • Multi-agent framework for intent-aware IFC and graph generation. • Automated zero-shot reconstruction across laser-scan, simulated, and RGB-D datasets. • Topology-aware IFC generation ensuring wall–wall and wall–slab connectivity. • Intent-adaptive reconstruction levels controlled via natural-language queries.
Pan et al. (Thu,) studied this question.