.png){kind=icon}
.png){kind=icon}
Return
LLM-enabled multi-agent framework for automated Scan-to-BIM and Scan-to-Graph reconstruction
.png){kind=icon}
OA
AI
Y
M
J
J
M
I
DOI：10.1016/j.autcon.2026.107003.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• 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.
Keywords:
Building Information Modeling (BIM)
Large Language Models (LLMs)
Scan-to-BIM
Scan-to-Graph
Digital twin
Multi-agent framework
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
11.5
Papers:
6.1K
Citations:
4.2W
Organization
Cited Papers