Jul 2026· Proceedings of the international conference of contemporary affairs in architecture and urbanism-ICCAUA· Vol 9, pp. 2610375· 0 citations
TL;DR
Whether AI-informed conceptual design generates spatial configurations that differ measurably from conventional approaches is examined, which will contribute to the development of data-driven, adaptive, and user-centered architectural methodologies.
Abstract
Integrating artificial intelligence (AI) into the built environment has greatly improved building automation and performance optimization. However, the potential of AI to inform early spatial configuration, user-oriented planning, and its role in shaping architectural decisions at the conceptual design stage have not been well studied. This study aims to compare traditional architectural design processes with AI-informed design approaches at the conceptual stage. An experimental comparative design model is employed in which two parallel design scenarios are developed for the same prototype: a conventional, architect-led concept design and an AI informed concept design. The comparative evaluation framework is structured around five multidimensional criteria: Space Utilization Efficiency, Daylight Performance, Circulation Optimization, User Scenario Compatibility, and Spatial Adaptation Capacity. This study examines whether AI-informed conceptual design generates spatial configurations that differ measurably from conventional approaches. The findings will contribute to the development of data-driven, adaptive, and user-centered architectural methodologies.
Architectural design requires balancing creativity with practical constraints, yet many early-stage decisions are made intuitively with limited evaluation of their impacts. In the context of increasing demand for affordable housing, there is a need for design workflows that better integrate efficiency, constructibility, and material performance at the schematic design stage. This thesis investigates how data-informed computational design workflows can support more evidence based early decision making within timber prefabricated housing design. Using a Research by Design (RbD) methodology supported by data-informed evaluation, the study combines iterative prototyping with computational evaluation to compare prefabricated timber systems within a four-unit medium-density housing proposal. Two evaluative matrices were developed: one to assess prefabrication systems across material use, life cycle considerations, performance, and construction criteria, and another to evaluate how architectural design decisions influenced efficiency and spatial outcomes across multiple design iterations. Functioning as decision-making tools, the matrices enabled qualitative design intentions to be tested against quantitative performance criteria while avoiding over-determination of architectural exploration. The findings demonstrate that the iterative, computationally informed design workflow effectively integrates evaluation with architectural
intent. The analysis clarifi es how early design decisions influence efficiency and spatial quality while also highlighting the limitations of computational precision and the continuing need for architectural judgment. Overall, the research shows that data-informed workflows can enhance design decision-making without replacing intuition, supporting more transparent, evidence-based, and efficient design processes.
This paper proposes a governance-aware methodological framework for the integration of Cognitive Artificial Intelligence into marine CAD environments. Unlike existing approaches that focus on isolated optimization or prediction tasks, the proposed framework introduces a structured architecture combining engineering knowledge corpora, hybrid AI reasoning, and CAD-based interaction within a traceable and regulatory-aware workflow. The contribution of this work is methodological rather than domain-exhaustive. The framework is illustrated through a conceptual pipe routing use case, selected as a representative high-constraint design subsystem involving spatial reasoning, compliance verification, and iterative coordination. A normalized performance evaluation model is defined to estimate improvements in design efficiency, convergence, compliance validation and rework reduction. Although the validation is conceptual, the results are consistent with reported improvements in AI-assisted engineering workflows. The proposed framework gives a basis for integrating AI into marine CAD environments, aligned with newer digital ship design and Shipyard 4.0 approaches.
D. Casado, R. Fernández· Journal of Marine Science an...· 0 citations
This work presents an alternative, result-oriented, data-driven method based on generative AI to assist engineers in the conceptual design phase of bridge construction, and demonstrates that result-oriented, data-driven generative models can support early-stage bridge topology exploration under controlled conditions.
Aswin Lal, Chongjie Kang, B. Özcan et al.· Journal of computing in civi...· 0 citations
The increasing digitization of construction management has created opportunities for artificial intelligence (AI), robotics, cloud architectures, and large language models (LLMs) to support planning, coordination, monitoring, and operational decision-making. However, scalability remains a fundamental challenge because construction environments are characterized by heterogeneous workflows, distributed information, changing operational conditions, and uneven levels of technological adoption. This research and review paper examines the principal scalability constraints affecting AI-driven construction management and investigates how robotics and LLM integration can address selected operational and informational limitations. The study adopts a conceptual qualitative methodology based on grounded-theory principles, systematic interpretation of the provided literature, and cross-domain synthesis. The analysis identifies four interconnected scalability dimensions: technological infrastructure, organizational routines, human-system interaction, and learning and decision-support capacity. Cloud-oriented architectures provide a foundation for distributed computational access, while research on learning systems indicates that sustained technology adoption depends on perceived usefulness, quality, task value, and user capability. Grounded-theory studies further indicate that organizational routines and methodological processes influence how emerging technologies become embedded in operational practice. Within this framework, robotics can extend AI from informational decision support toward physical execution, whereas LLMs can improve the accessibility, interpretation, and coordination of heterogeneous construction information. The paper proposes an integrated scalability framework in which infrastructure, organizational routines, human learning, LLM-based intelligence, and robotic execution are treated as mutually dependent components rather than isolated technologies. The findings indicate that scalability should be understood not merely as increasing computational capacity but as the ability to expand AI-enabled construction processes without proportionally increasing coordination complexity, training requirements, or operational risk.
Takumi Suzuki, Mio Tanaka· International Journal of Adv...· 0 citations
This study analyzes how AI-generated design concepts, high-fidelity CGI renders, and BIM-based construction data can be integrated into a coherent project delivery workflow, with particular attention to the US residential and commercial interior design market.
Alina Stopina· Universal Library of Arts an...· 0 citations
High-density school design has become an important challenge in rapidly urbanizing cities, where land scarcity, increasing educational demand, and evolving pedagogical models generate multiple and interrelated design constraints. Although a wealth of design experience has accumulated through the execution of numerous school planning projects, this knowledge remains fragmented across architectural publications and project narratives. Existing studies have primarily focused on evaluating built environments or individual cases, and limited attention has been paid to how dispersed architectural design reasoning can be systematically extracted, organized, and represented. This study was conducted to explore how AI-assisted semantic modeling can support the extraction and organization of architectural design knowledge from large-scale design discourse through a human–AI collaborative interpretation framework. Using a corpus of 330 documents reporting school design in Shenzhen published between 2017 and 2024, the proposed framework integrates BERTopic-based semantic modeling, scenario–strategy coding, network analysis, and document-based architectural interpretation to establish a continuous workflow from architectural discourse to structured knowledge representation and spatial interpretation. The results reveal a density-conditioned knowledge structure consisting of six interconnected design agendas, 25 recurrent design scenarios, 44 original design strategies, 17 core strategies, four strategy clusters, and four document-supported spatial response patterns. The findings demonstrate that high-density school design knowledge is organized through recurring problem–strategy relationships rather than isolated project solutions. Through human–AI collaborative interpretation, fragmented design narratives are transformed into hierarchical representations linking design concerns, scenarios, strategies, and spatial organizations. The aim of the proposed framework is not to automate architectural decision-making or generate implementation-ready design solutions but to provide a methodological foundation for AI-assisted architectural knowledge retrieval, knowledge representation, and future multimodal design intelligence systems.
Xiaoyu Lin, Xingjie Zhu, Gang Yu· Buildings· 0 citations