The Impact of Generative AI on Architectural Conceptual Design: Performance, Creative Self-Efficacy and Cognitive Load

2026-01-15

AI Summary

This study investigates the impact of generative AI on design performance, creative self-efficacy, and cognitive load in architectural conceptual design. Through a controlled experiment, it compares design outcomes produced by students working independently, with generative AI assistance, or with access to an online case repository, integrating expert evaluations and subjective self-report measures to examine differences across varying levels of design expertise. The findings indicate that while generative AI does not uniformly enhance overall design performance, it significantly improves output quality for novice designers—albeit at the cost of reduced creative self-efficacy. Moreover, specific prompting strategies are shown to effectively mitigate cognitive load. These results illuminate the nuanced, experience-dependent effects of generative AI in design education and suggest pathways for optimizing human–AI collaboration.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Philosophy and Ethics of AI: Artificial General Intelligence

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Our study examines how generative AI (GenAI) influences performance, creative self-efficacy, and cognitive load in architectural conceptual design tasks. Thirty-six student participants from Architectural Engineering and other disciplines completed a two-phase architectural design task, first independently and then with external tools (GenAI-assisted condition and control condition using an online repository of existing architectural projects). Design outcomes were evaluated by expert raters, while self-efficacy and cognitive load were self-reported after each phase. Difference-in-differences analyses revealed no overall performance advantage of GenAI across participants; however, subgroup analyses showed that GenAI significantly improved design performance for novice designers. In contrast, general creative self-efficacy declined for students using GenAI. Cognitive load did not differ significantly between conditions, though prompt usage patterns showed that iterative idea generation and visual feedback prompts were linked to greater reductions in cognitive load. These findings suggest that GenAI effectiveness depends on users'prior expertise and interaction strategies through prompting.

Problem

• Generative AI
• Architectural Design
• Creative Self-Efficacy
• Cognitive Load
• Design Performance

Innovation

• generative AI
• architectural design
• creative self-efficacy
• cognitive load
• prompting strategy