Collaborative Facade Design with LLM-Based Multi-Agent Systems Using Reclaimed Building Components

Pritha Jacob1, Ioanna Mitropoulou1, Pei-Yu Wu2, Catherine De Wolf1
1 ETH Zurich, Zurich, Switzerland
2 Delft University of Technology, Delft, The Netherlands
DOI: 10.35490/EC3.2026.244
Abstract: The potential for material reuse is restricted by the lack of methods for integrating reclaimed materials into facade design workflows. This paper presents a multi-agent pipeline using LLMs to support integrating reclaimed materials into facade design. Tested through a web application in two design modes: a collaborative mode, where human and LLM collaborate, and an independent mode, without human guidance; the users reported the collaborative mode to be more useful. The proposed AI-human collaboration framework improved the tasks of searching for materials, evaluating options, and visualizing design iterations, highlighting the value of AI-driven design frameworks in encouraging reuse in architecture.
Keywords: AI agents, Circularity, Facade design, Large Language Models

Presentation video

Successfully submitted

Your submission has been received. We will review your details and contact you soon.