Modeling Sequential Design Actions as Designer Externalization on an Infinite Canvas

2026-03-12

AI Summary

This study investigates how AI agents influence designers’ cognitive externalization and workflow within infinite canvas environments. Through field studies and sequential action analysis, the authors model 5,838 design actions, integrating spatial layout data from multimodal artifacts to propose a “Generate–Curate” cycle. This model reveals a three-stage dynamic mechanism in which the AI’s role evolves from a divergent catalyst to a convergent curator. Findings indicate that while AI does not extend active design time, it significantly reconfigures the distribution of cognitive load. The work provides empirical evidence and a behavioral framework to inform the development of phase-adaptive AI tools for human-AI collaborative design.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Mechanism Design

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• infinite canvas
• designer externalization
• AI agent
• sequential design actions
• human-AI collaboration

Innovation

• infinite canvas
• design externalization
• human-AI co-evolution
• sequence analysis
• phase-adaptive AI