Student Perceptions of Large Language Models Use in Self-Reflection and Design Critique in Architecture Studio

2026-01-19

AI Summary

This study investigates how large language models (LLMs) can be effectively leveraged in architectural design studios to support student self-reflection and design critique beyond mere generative applications. Employing a mixed-methods approach—combining surveys and semi-structured interviews—the research proposes positioning the LLM as a “cognitive mirror,” a collaborative agent that fosters critical thinking rather than functioning solely as a tool. Findings indicate that students utilize the LLM to structure their thinking, neutralize peer feedback dynamics, and integrate insights post-critique, thereby significantly enhancing the depth of reflection and learning efficiency. Additionally, this approach mitigates social anxiety and cognitive overload commonly associated with traditional critique settings. The proposed framework offers both theoretical grounding and practical pathways for the innovative integration of AI in design education.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

This study investigates the integration of Large Language Models (LLMs) into the feedback mechanisms of the architectural design studio, shifting the focus from generative production to reflective pedagogy. Employing a mixed-methods approach with surveys and semi structured interviews with 22 architecture students at the Singapore University of Technology and De-sign, the research analyzes student perceptions across three distinct feed-back domains: self-reflection, peer critique, and professor-led reviews. The findings reveal that students engage with LLMs not as authoritative in-structors, but as collaborative"cognitive mirrors"that scaffold critical thinking. In self-directed learning, LLMs help structure thoughts and over-come the"blank page"problem, though they are limited by a lack of contex-tual nuance. In peer critiques, the technology serves as a neutral mediator, mitigating social anxiety and the"fear of offending". Furthermore, in high-stakes professor-led juries, students utilize LLMs primarily as post-critique synthesis engines to manage cognitive overload and translate ab-stract academic discourse into actionable design iterations.

Problem

• Large Language Models
• self-reflection
• design critique
• architectural education
• student perception

Innovation

• Large Language Models
• reflective pedagogy
• cognitive mirror
• design critique
• architectural education