Aug 2026· Buildings· Vol 16, pp. 3259· 0 citations· 34 references
TL;DR
This study explores 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 to provide a methodological foundation for AI-assisted architectural knowledge retrieval, knowledge representation, and future multimodal design intelligence systems.
Abstract
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.
This article reports a structured scoping-style review, rather than a meta-analysis, of generative artificial intelligence (GenAI) applications in architectural conceptual design. Searches were conducted in Web of Science, Scopus, Dimensions and CNKI for English- and Chinese-language records, supplemented by targeted forward and backward citation chasing. The evidence base distinguishes coded studies from contextual references and comprises 58 coded studies and 15 contextual references published between 2018 and 2026. The literature was coded by technical type, design stage, input modality, output modality, evaluation strategy, editability, and stated limitation. The synthesis identifies four interrelated domains: LLM-based semantic and knowledge support, diffusion-based conceptual visualization, spatially conditioned layout and 3D scene generation, and BIM/parametric coupling within human-AI workflows. The review indicates that current research is strongest in atmospheric visualization and prompt-mediated exploration, while evidence for architectural validity, downstream editability, regulatory checking, and professional accountability remains limited. Four cross-cutting challenges—controllability, evaluability, translatability, and responsibility—are operationalized as review-derived evaluation dimensions. GenAI is therefore better understood as a representational and workflow technology for early-stage exploration than as an autonomous architectural designer.
Concept generation is one of the most challenging stages of architectural design, as translating abstract ideas into coherent spatial concepts is often difficult for students and designers. This research investigates storytelling as a conceptual generator in architectural design by examining how narrative structures influence concept development and spatial organization. A comparative experimental study was conducted with eighty first-year architecture students. The students were distributed into two groups with balanced academic performance based on GPA. The control group followed a conventional concept development approach, while the experimental group applied a narrative-driven design method in which stories were translated into spatial compositions through stages of interpretation, abstraction, and spatial transformation. Student projects were evaluated through a multi-jury review system and analyzed using descriptive statistics and independent samples t-tests. The results show that narrative-driven design significantly improved conceptual clarity, spatial composition, and creativity, highlighting storytelling as a structured framework for generating architectural concepts. The study contributes empirical evidence to architectural design education by demonstrating the effectiveness of narrative-driven approaches in supporting concept generation and spatial design development.
Shden Abusafieh· Proceedings of the internati...· 0 citations
Data visualization research has developed many influential forms of design knowledge, including perceptual principles, design guidelines, process models, and formalized representations of design constraints. These contributions have been effective at articulating explicit, portable, and codified forms of knowledge. Yet the broader landscape on which visualization design depends remains less clearly articulated, especially with respect to intermediate-level knowledge, precedents, tacit repertoires, and situated forms of knowing. In this paper, we draw on design theory to map this broader landscape of design knowledge in data visualization. Through this lens, we show how visualization research has built substantial strengths in some regions while leaving others comparatively underarticulated. We further argue that visualization design depends not only on knowledge artifacts such as theories, guidelines, and patterns, but also on knowledge-in-use---the situated interpretation, adaptation, and coordination of multiple forms of knowing in concrete design situations. This broader account has implications for how the field conceptualizes design expertise, evaluates and develops scholarly contributions, and approaches AI-assisted design. Rather than treating visualization design as either fully formalizable or wholly resistant to computational support, we argue for a differentiated view in which computational systems can support some forms of design knowing, while others remain inseparable from human judgment, contextual interpretation, and the ongoing reorganization of design work in practice.
Paul C. Parsons, Colin M. Gray, Ali Baigelenov· 1 citation
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.
Sanam Rezaeifam, Seyed Babak Ehsani Oskouei, Gökçen Firdevs Yücel Caymaz· Proceedings of the internati...· 0 citations
Architectural space is produced through decisions about form, material, construction, structure, program, and environment, and design education centers on it. In design studios, generative AI (GenAI) most often enters through visual representation, raising the risk we term the visualization trap: images can appear resolved before their tectonic implications are worked out. This exploratory study examines GenAI participation through protocol analysis of the documented process traces of 18 students in a single, AI-aware bioclimatic design studio, yielding 1107 protocols. The TRACE-SC methodology maps space-constituting components, GenAI use types, design phases, and cognitive breaking points; reliability was examined through a blind expert coding audit and cross-LLM comparison. GenAI appeared in 44.2% of protocols (489/1107), where visual generation and information gathering accounted for 81.2% (397/489). Suggestions were transformed before use in 68.1% (333/489) and adopted verbatim in 0.4% (2/489); interaction was designer-initiated. Cognitive breaking points appeared in 2.2% of protocols (24/1107), with indirect evidence in 70.8% (17/24). GenAI proves more than a visual production tool, but its engagement is limited, episodic, and designer-steered rather than a routine design partnership—partial support for the proposition. The transferable contribution is the TRACE-SC framework and codebook; its patterns describe this studio and invite comparison elsewhere.
