Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modeling Sequential Design Actions as Designer Externalization on an Infinite Canvas

Yejin Yun, Seung Won Lee, Jiin Choi, Kyung Hoon Hyun

Abstract

Infinite canvas platforms are becoming central to contemporary design practice, enabling designers to externalize cognition through the spatial arrangement of multimodal artifacts. As AI agents increasingly generate and organize content within these environments, their impact on designers' externalization processes remains underexplored. We report a field study with eight professional designers comparing workflows with and without an AI organizing agent. Through a sequence analysis of 5,838 design actions, we identify three key shifts: (1) AI integration reallocates cognitive effort from spatial management to content curation and relational structuring, without increasing active time; (2) a characteristic generate-and-curate cycle emerges in which designers' demands on the agent intensify while the agent's functional role adapts; and (3) AI's role evolves from a divergent catalyst in early stages to a convergent curator in later phases. These findings offer a behavioral model for designing phase-adaptive AI tools that support human-AI co-evolution on infinite canvases.

Modeling Sequential Design Actions as Designer Externalization on an Infinite Canvas

Abstract

Infinite canvas platforms are becoming central to contemporary design practice, enabling designers to externalize cognition through the spatial arrangement of multimodal artifacts. As AI agents increasingly generate and organize content within these environments, their impact on designers' externalization processes remains underexplored. We report a field study with eight professional designers comparing workflows with and without an AI organizing agent. Through a sequence analysis of 5,838 design actions, we identify three key shifts: (1) AI integration reallocates cognitive effort from spatial management to content curation and relational structuring, without increasing active time; (2) a characteristic generate-and-curate cycle emerges in which designers' demands on the agent intensify while the agent's functional role adapts; and (3) AI's role evolves from a divergent catalyst in early stages to a convergent curator in later phases. These findings offer a behavioral model for designing phase-adaptive AI tools that support human-AI co-evolution on infinite canvases.
Paper Structure (17 sections, 4 figures, 1 table)

This paper contains 17 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Study Design
  3. Sequential Design Action Classification Framework
  4. Results and Discussion
  5. Design Workflow Redistribution Without Increased Effort (RQ1)
  6. Sequential design action mining, From Spatial Management Overhead to Creative Flow: Shift in Collaborative Loops (RQ2)
  7. Phase-Dependent Evolution of Agent Partnership (RQ3)
  8. Early phase, Idea Amplifier.
  9. Mid phase, Co-evolutionary Structuring.
  10. Late phase, Convergent Curation.
  11. Conclusion and Limitation
  12. Details of Sequential Design Action Classification Framework
  13. Data Collection and Preprocessing
  14. Action Magnitude Quantification Thresholds
  15. Active Time and Segmentation
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Infinite-canvas workspace used in the study. Designers externalize ideas by collecting, spatially arranging, and connecting multimodal artifacts (e.g., images, notes, connectors). Both Baseline and Agent$_{\text{organizer}}$ conditions support prompt generation and image editing within the canvas.
  • Figure 2: Workflow of the Agent$_{\text{organizer}}$ condition. The AI organizing agent observes designers' artifact collections on the canvas, forms semantically coherent clusters, and leverages these clusters as implicit prompts for subsequent image generation.
  • Figure 3: Comparative analysis of design action distributions and statistical significance between Baseline and Agent$_{\text{organizer}}$ conditions. Left: Percentage distribution of 11 design actions across conditions. Right: Z-scores indicating statistically significant changes in action frequency, highlighting decreases in Relocate and increases in AgentGen and Relate.
  • Figure 4: Temporal evolution of design actions across Early, Mid, and Late phases Agent$_{\text{organizer}}$ vs. Baseline. Heatmaps show the percentage distribution of top design actions over time, revealing reduced Relocate activity and increased content creation and relational structuring in the agent condition.