Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Conversational Agents as Catalysts for Critical Thinking: Challenging Design Fixation in Group Design

Soohwan Lee, Seoyeong Hwang, Kyungho Lee

TL;DR

The paper addresses design fixation and rigid group dynamics in design processes by exploring LLM-based conversational agents that act as dissents, challenging AI-generated recommendations and group consensus. It proposes a shift from AI as a mere recommender to a proactive critical partner, leveraging Retrieval-Augmented Generation to ground counterarguments and support real-time, context-aware interventions. The authors outline scenarios, a hypothetical trade-off model between critical thinking and designer satisfaction, and a set of design considerations (timing, argument clarity, adaptive stimulation, and role flexibility) to guide development of practical CA tools. The work aims to stimulate discussion at the intersection of design research and GenAI, contributing to ethical, reflective practices and providing directions for future tools and knowledge-management approaches in group design.

Abstract

This paper investigates the potential of LLM-based conversational agents (CAs) to enhance critical reflection and mitigate design fixation in group design work. By challenging AI-generated recommendations and prevailing group opinions, these agents address issues such as groupthink and promote a more dynamic and inclusive design process. Key design considerations include optimizing intervention timing, ensuring clarity in counterarguments, and balancing critical thinking with designers' satisfaction. CAs can also adapt to various roles, supporting individual and collective reflection. Our work aligns with the "Death of the Design Researcher?" workshop's goals, emphasizing the transformative potential of generative AI in reshaping design practices and promoting ethical considerations. By exploring innovative uses of generative AI in group design contexts, we aim to stimulate discussion and open new pathways for future research and development, ultimately contributing to practical tools and resources for design researchers.

Conversational Agents as Catalysts for Critical Thinking: Challenging Design Fixation in Group Design

TL;DR

The paper addresses design fixation and rigid group dynamics in design processes by exploring LLM-based conversational agents that act as dissents, challenging AI-generated recommendations and group consensus. It proposes a shift from AI as a mere recommender to a proactive critical partner, leveraging Retrieval-Augmented Generation to ground counterarguments and support real-time, context-aware interventions. The authors outline scenarios, a hypothetical trade-off model between critical thinking and designer satisfaction, and a set of design considerations (timing, argument clarity, adaptive stimulation, and role flexibility) to guide development of practical CA tools. The work aims to stimulate discussion at the intersection of design research and GenAI, contributing to ethical, reflective practices and providing directions for future tools and knowledge-management approaches in group design.

Abstract

This paper investigates the potential of LLM-based conversational agents (CAs) to enhance critical reflection and mitigate design fixation in group design work. By challenging AI-generated recommendations and prevailing group opinions, these agents address issues such as groupthink and promote a more dynamic and inclusive design process. Key design considerations include optimizing intervention timing, ensuring clarity in counterarguments, and balancing critical thinking with designers' satisfaction. CAs can also adapt to various roles, supporting individual and collective reflection. Our work aligns with the "Death of the Design Researcher?" workshop's goals, emphasizing the transformative potential of generative AI in reshaping design practices and promoting ethical considerations. By exploring innovative uses of generative AI in group design contexts, we aim to stimulate discussion and open new pathways for future research and development, ultimately contributing to practical tools and resources for design researchers.
Paper Structure (7 sections, 1 figure)

This paper contains 7 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Beyond Recommendations: Enhancing Critical Thinking with Generative AI
  3. Challenges and Opportunities of Using Conversational Agents in Group Design
  4. Potential Scenario and Applications of Conversational Agents in Group Design Process
  5. Balancing Critical Thinking with Designer Satisfaction and Motivation
  6. Potential Design Considerations
  7. Conclusion

Figures (1)

  • Figure 1: Hypothetical Model of the Trade-off between Critical Thinking and Designer Satisfaction in Group Design: This model illustrates how an LLM-based conversational agent (CA) acting as a naysayer can influence critical thinking and group dynamics. In a virtuous cycle, moderate stimulation of critical thinking (a) enhances design outcomes (b), increasing designers' satisfaction (c), motivating continued use of CAs (e), and fostering more critical thinking (d), with minimal negative impact (f). Conversely, in a vicious cycle, excessive stimulation (g) leads to cognitive overload and negative group dynamics (l), decreasing satisfaction (k), reducing motivation to use CAs (j), lowering design quality (h), and further diminishing satisfaction and motivation (i). This model is theoretical and has not been empirically validated.