aalto1 untyped-item.component.html
From Automation to Intelligence : An AI agent for spatial reasoning and 3D co-design
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Date
Department
Major/Subject
Mcode
Degree programme
Language
en
Pages
10
Series
eCAADe 2025 Confluence: Proceedings of the 43rd Conference on Education and Research in Computer Aided Architectural Design in Europe, Volume 1, issue 1, pp. 431-440, eCAADe proceedings
Abstract
Spatial understanding and reasoning are core cognitive abilities in architectural design, yet existing AI tools remain limited to automation without interpretability or goal-driven logic. This study introduces a 3D Co-Design Assistant that integrates spatial perception, reasoning, and modeling via a Large Language Model (LLM)-driven agent framework. Operating through a real-time perception–reasoning–action loop, the system enables AI to generate design suggestions and autonomously execute modeling commands in a 3Denvironment. Unlike previous black-box generative models, the assistant produces interpretable design logic grounded in structured scene data and user input. Its capabilities are evaluated through controlled human judgment and co-creation experiments, where participants often misidentified AI suggestions as human-generated, and rated many proposals as rational and contextually appropriate—demonstrating early signs of human-like spatial cognition. By bridging semantic reasoning with executable modeling behaviors, the proposed framework offers a novel approach to AI-assisted design beyond conventional automation, highlighting the potential of intelligent agents to support architects in iterative spatial thinking, stimulate creative alternatives, and facilitate the integration of AI into early-stage architectural workflows.
Description
Other note
Citation
Zhong, X, Li, Y, Fricker, P & Zhang, X 2025, From Automation to Intelligence : An AI agent for spatial reasoning and 3D co-design. in A Gönenç Sorguç, M Kruşa Yemişcioğlu, S Buket Erol, M Eren Bük, D Güney, B Aktaş Sulayıc & M Akol (eds), eCAADe 2025 Confluence : Proceedings of the 43rd Conference on Education and Research in Computer Aided Architectural Design in Europe. 1 edn, vol. 1, eCAADe proceedings, eCAADe, Brussels, pp. 431-440, International Conference on Education and Research in Computer Aided Architectural Design in Europe, Ankara, Türkiye, 01/09/2025. https://doi.org/10.52842/conf.ecaade.2025.1.431