Generative artificial intelligence has swept into design research and practice, with popular image generators and language model interfaces now being used across disciplines and design stages. The multimodal language models exhibit fundamentally different characteristics from earlier machine learning approaches, and present unique challenges and opportunities for designers. A key question for design research arises: How can the capabilities of these large multimodal models become part of our design tools? This work investigates how the recent development of reasoning language models in particular can be utilized for early stage exploratory design. We outline a set of principles to build effective tools with these models by drawing from research in artificial intelligence. Specifically, we explore the application of the new reasoning model paradigm in computational design scripting. We present a system which successfully generates computer-aided design (CAD) scripts in Grasshopper. The system is compared to existing CAD AI approaches for its capabilities and characteristics. High latency and the absence of a user-model feedback loop still restrict real-time exploration in our system. Our developed principles can further inform broad exploratory tools and motivate inquiries into multimodal reasoning for design. By demonstrating a new CAD approach, we show large models’ utility as creative tools. Future research should address latency, enhance interactivity, and address other design tasks beyond CAD.

This work contributes to the evolving discourse on biodigital architecture by examining how generative artificial intelligence (AI) and extended reality (XR) systems can be combined to create immersive urban environments. Focusing on the case study of “Osmosis”, a series of large-scale public installations, this work proposes a methodological framework for real-time architectural composition in XR using diffusion models and interaction. The project reframes the architectural façade as a semi permeable membrane, through which digital content diffuses in response to environmental and user inputs. By integrating natural language prompts, multimodal input, and AI-generated visual synthesis with projection mapping, Osmosis advances a vision for urban architecture that is interactive, data-driven, and sensorially rich. The work explores new design territories where stochastic form-making and real-time responsiveness intersect, and positions AI as an augmentation of architectural creativity rather than its replacement.

Spatial layout planning is a complex architectural problem involving numerous constraints and potential solutions. Conventional methods can be tedious and time-consuming, prompting recent research toward automated layout generation to create more design alternatives and ease the process. Presented here is a procedural model for spatial layout design, inspired by methods in game design and based on cellular automata. The model considers user inputs such as geometry, topology (direct and indirect adjacencies), and privacy requirements to automatically generate design options. The generated layouts satisfy input requirements and are generated deterministically through specification of seeds that have virtually no upper limit. The proposed method aims to support architects and designers in the layout planning process by combining algorithmic efficiency of cellular automata with a top-down approach to adhere to user-defined constraints. This method also has potential for integrating additional design objectives and user interaction in future developments.

Girih patterns, prominent in Islamic art and architecture, exhibit complexity and adherence to specific mathematical rules. Understanding and preserving these patterns requires knowledge of their design processes and underlying rules which require transferable knowledge of computation. This paper aims to generate three prominent Girih patterns in Islamic architecture, namely ‘ Hasht-Chahar-Lengeh’, ‘ Hasht-Panj’, and ‘ Hasht-Bazoubandi’, gaining insights from graph theory definitions and algorithmic design within the Grasshopper program. Employing the graph theory, it pioneers a novel approach to pattern generation. The approach facilitates the faithful reproduction of existing patterns and enables the generation of entirely new designs with a comprehensive comparison of both computational methodologies.

The increasing development in the computational field that allowed software and hardware advances enables more refined building performance analysis. Simulation-based optimization (SBO) methods allow high standards to be achieved by combining parametric modeling, simulation, and optimization methods. However, SBO methods still need development, especially regarding the correct choice of the optimization algorithm based on the specific characteristics of each problem. This study proposes a multi-objective optimization algorithms benchmark by comparing seven multi-objective optimization algorithms: RBFMOpt, NSGA2, MHACO, NSPSO, MOEA/D, HypE, and SPEA2, across nine building-related problems, including thermal, energy, and daylight simulation. The problems varied from 5 to 18 discrete, continuous, and mixed parameters. The objective functions varied between two and three. We used the hypervolume indicator, IGD+, GD+, and EPS + to compare algorithms’ performance and assess the tendency to reduce computational costs. We also performed the Kruskal-Wallis non-parametric test to analyze the impact of multiple runs on the hypervolume indicator. The results showed that RBFMOpt and HypE perform best across all problems. However, RBFMOpt tends to reduce computational costs since the algorithm requires fewer simulations to obtain the best results.

This research introduces an innovative Augmented Reality (AR) workflow for Human-Robot Interaction (HRI) in timber construction. The approach leverages human dexterity and adaptability alongside the strength and precision of robotic arms to assemble timber structures connected by wood-wood connections. While research in the field of automated construction generally focuses on singular interactions, such as robot agents carrying components and human agents attaching them, this paper explores multiple degrees of interaction involving cooperation or collaboration between agents. A new algorithmic framework is developed to automate the generation of holographic instructions and allocate assembly tasks to human and robot agents according to their abilities. The application to a full-scale demonstrator reveals that certain elements necessitate collaboration for assembly, while others can exclusively be assembled manually or robotically. Ultimately, the research also highlights the benefits of AR in assisting manual assembly, simulating robot trajectories, and increasing safety during collaborative tasks.

This study addresses the notable absence of comprehensive syntheses and bibliometric analyses concerning the utilization of spatial technology within urban heritage preservation contexts. The research aims to elucidate the current status, methodologies, advancements, and future trajectories of spatial technology applications in urban heritage preservation. Employing a systematic literature review and bibliometric analysis, the study examines pertinent 157 literature through Scopus, categorizes research applications, analyzes bibliometric data, evaluates influence rankings across multiple dimensions, identifies historical trends, and outlines prospective directions. The study findings unveil the evolving characteristics of spatial technology applications. Firstly, it reveals a gradual development trend, with spatial technologies experiencing an annual growth rate of 7.7% between 2010 and 2020. Nevertheless, a significant disparity persists, with more than 63.2% of countries still fully integrating spatial technology on-site at heritage sites. Furthermore, the study highlights varied collaboration levels between research institutions, with limited international cooperation and exchange, particularly evident between developed and developing nations. Lastly, the increasing demand for interdisciplinary research signals a shift towards fostering innovative approaches and solutions in heritage site preservation and management.

Hybrid girihs refer to Islamic geometric patterns that include various stars/rosettes in their final pattern. In this paper, we first identified historical hybrid girihs and then categorized them based on symmetry groups and the number of stars/rosettes folds. In the next step, we analyzed the existing hybrid girihs to identify the generative parameters and present a method for generating historical and novel systematic and non-systematic hybrid girihs. The proposed method of this paper is a computational and parametric approach based on the symmetry groups theory. Its general steps include generating the minimal essential information (template motif) within the fundamental region, applying appropriate symmetry operations on the content of the fundamental region to create the content of the unit girih, and replicating the content of the unit girih in a suitable network according to the symmetry group to create the whole pattern. Our method is used to generate hybrid girih for adorning surfaces in digital spaces and for constructing facade modules (adorned with Islamic geometric patterns) and interior decorative partitions and furniture in physical spaces according to the aesthetic judgment of users.

This article describes generative algorithms and Digital Fabrication techniques with organic materials to create complex 3D objects for industrial design, sculpture, and architecture. Experimental artistic production using these algorithms concluded with a solution based on programmable meshes, which use identifiers to control the topological characteristics of vertices during the modeling process. On the other hand, the hybridization of analog and digital techniques was explored through fabrication. Comparing artistic production and hybrid techniques with generative AI, we will discuss topics of Computational Creativity in art, industrial design, and architecture. The programmable meshes solution, combined with hybrid fabrication processes, enables an incredible variety of complex forms, stimulates artistic creativity, and provides flexible feedback to bypass some Digital Fabrication issues. Our findings also elucidate the importance of original technology development and cultural identity in fostering creative and culturally inclusive technologies for art and education.