Sketch2BIM: A Multi-Agent Human-AI Collaborative Pipeline to Convert Hand-Drawn Floor Plans to 3D BIM

arXiv:2510.20838 · cs.AI, cs.MA · Submitted 2025-10-16 · Read on arXiv

cs.AI, cs.MA

Submitted: 2025-10-16

Updated: 2025-10-16

Journal ref: Automation in Construction, Volume 189, 2026, 106984, ISSN 0926-5805

DOI: 10.1016/j.autcon.2026.106984

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 1× in this paper · explained in 1 episode
• F1 Score — 1× in this paper · explained in 3 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes

Sources

• BIMgent: Towards Autonomous Building Modeling via Computer-use Agents
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework
• MM-LLMs: Recent Advances in MultiModal Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems