Research

Paper

AI LLM February 25, 2026

A Taxonomy of Human--MLLM Interaction in Early-Stage Sketch-Based Design Ideation

Authors

Weiayn Shi, Kenny Tsu Wei Choo

Abstract

As multimodal large language models (MLLMs) are increasingly integrated into early-stage design tools, it is important to understand how designers collaborate with AI during ideation. In a user study with 12 participants, we analysed sketch-based design interactions with an MLLM-powered system using automatically recorded interaction logs and post-task interviews. Based on how creative responsibility was allocated between humans and the AI, we predefined four interaction modes: Human-Only, Human-Lead, AI-Lead, and Co-Evolution, and analysed how these modes manifested during sketch-based design ideation. Our results show that designers rarely rely on a single mode; instead, human-led and AI-led roles are frequently interwoven and shift across ideation instances. These findings provide an empirical basis for future work to investigate why designers shift roles with AI and how interactive systems can better support such dynamic collaboration.

Metadata

arXiv ID: 2602.22171
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-02-25
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22171v1</id>\n    <title>A Taxonomy of Human--MLLM Interaction in Early-Stage Sketch-Based Design Ideation</title>\n    <updated>2026-02-25T18:18:02Z</updated>\n    <link href='https://arxiv.org/abs/2602.22171v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22171v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>As multimodal large language models (MLLMs) are increasingly integrated into early-stage design tools, it is important to understand how designers collaborate with AI during ideation. In a user study with 12 participants, we analysed sketch-based design interactions with an MLLM-powered system using automatically recorded interaction logs and post-task interviews. Based on how creative responsibility was allocated between humans and the AI, we predefined four interaction modes: Human-Only, Human-Lead, AI-Lead, and Co-Evolution, and analysed how these modes manifested during sketch-based design ideation. Our results show that designers rarely rely on a single mode; instead, human-led and AI-led roles are frequently interwoven and shift across ideation instances. These findings provide an empirical basis for future work to investigate why designers shift roles with AI and how interactive systems can better support such dynamic collaboration.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-02-25T18:18:02Z</published>\n    <arxiv:comment>5 pages</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Weiayn Shi</name>\n    </author>\n    <author>\n      <name>Kenny Tsu Wei Choo</name>\n    </author>\n    <arxiv:doi>10.1145/3772363.3798524</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772363.3798524' rel='related' title='doi'/>\n  </entry>"
}