Computational Design and AI in Architecture: Methods, Evaluation, and Design Integration
Special Issue Information
Dear Colleagues,
Recent advances in computational design and artificial intelligence are rapidly reshaping architectural research and practice, and machine learning, generative algorithms, and data-driven methods are increasingly applied across multiple phases of the design process—from early ideation and spatial exploration to performance evaluation, optimization, and visualization. While these developments offer unprecedented opportunities, they also raise important questions regarding methodological rigor, architectural relevance, and meaningful integration into established design workflows.
This Special Issue aims to foreground computational and AI-driven approaches that are methodologically grounded and architecturally informed, rather than speculative or purely aesthetic applications. In particular, it seeks contributions that demonstrate how computational techniques are embedded within architectural reasoning, design decision-making, or evaluative frameworks. As generative AI tools become more accessible, it is increasingly important to distinguish visually compelling outputs from research that advances architectural knowledge through reproducible methods, explicit assumptions, and critical evaluation.
Architectural design differs from many other creative domains in that it must balance expressive qualities with functional, environmental, regulatory, and social constraints. Consequently, the application of AI in architecture requires careful consideration of how algorithmic outputs are interpreted, assessed, and refined by human designers. This Special Issue therefore emphasizes human–AI collaboration, where computational systems augment, rather than replace, architectural judgment. Contributions that articulate the role of designers in steering, constraining, or evaluating AI-driven processes are particularly encouraged.
Another central theme of this Special Issue is evaluation. While generative systems can produce large numbers of design alternatives, fewer studies rigorously assess these outputs in terms of spatial quality, environmental performance, constructability, perceptual impact, or usability. Papers that propose quantitative, qualitative, or hybrid evaluation methods—such as performance simulation, user studies, perceptual analysis, or benchmarking against architectural standards—are especially welcome. Recent work has also explored the use of Large Language Models (LLMs) and agentic AI approaches as analytical and reasoning components within design workflows, supporting semantic interpretation, comparative assessment, or multi-criteria evaluation alongside simulation-based methods.
The Special Issue further welcomes work that explores the integration of generative AI with existing architectural tools and workflows, including CAD, BIM, parametric modeling environments, and simulation platforms. Rather than treating AI as a standalone black box, such integration enables more transparent, controllable, and architecturally meaningful applications. Educational perspectives are also relevant, particularly studies that examine how computational and AI-based design methods are taught, learned, and critically assessed in academic settings.
Areas of interest include, but are not limited to, the following topics:
- Generative AI integrated with CAD or BIM systems;
- Machine learning for spatial analysis, layout generation, or form exploration;
- AI-assisted design decision-making and optimization;
- Human–AI collaborative frameworks;
- Computational evaluation of architectural performance and perception;
- Validation and benchmarking of AI-generated architectural outputs;
- Pedagogical approaches to computational and AI-driven design.
Submissions that are purely conceptual, prompt-only explorations, or image-based speculation without methodological grounding or evaluation fall outside the scope of this Special Issue.
By bringing together rigorously developed computational methods and architecturally grounded applications, this Special Issue aims to contribute to a more critical and constructive discourse on the role of AI in architecture, clarifying how emerging technologies can meaningfully inform architectural thinking, education, and practice.
Dr. Taro Narahara
Dr. Tomohiro Fukuda
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the Special Issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Architecture is an international peer-reviewed open access quarterly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- computational design
- AI in architecture
- large language models (LLMs)
- agentic AI systems
- machine learning
- human–AI collaboration
- architectural performance evaluation
- CAD/BIM integration
- VR/AR/MR research
- computational design education
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

