Publications / 2025 Proceedings of the 42nd ISARC, Montreal, Canada

Towards Agent: LLM-based Framework for Robotic Construction by Leveraging IFC

Song Du, Yan Gao, Wei Tong, Yiwei Weng
Pages 358-365 (2025 Proceedings of the 42nd ISARC, Montreal, Canada, ISBN 978-0-6458322-2-8, ISSN 2413-5844)
Abstract:

This work explores the integration of Large Language Model (LLM)-powered agents into robotic construction workflows. An LLM-based agent framework by leveraging standardized IFC format is proposed to guide robotic tasks, such as bricklaying and 3D concrete printing. Through a combination of tailored tools, prompt templates, and a CustomMemory module, the framework enables efficient extraction of building information and execution of robotic tasks. Finally, experimental validation in a simulated environment demonstrates the framework's potential to streamline robotic construction workflows from textual or voice commands to physical construction activities, while reducing redundant operations and enhancing reliability through thoughtful design.

Keywords: LLM Agents, Robotic Construction, IFC, BIM, 3D Concrete Printing