DesignerlyLoop: Forming Design Intent through Curated Reasoning for Human-LLM Alignment

TL;DR

DesignerlyLoop enhances human-LLM collaboration in design by enabling explicit inspection and reorganization of LLM reasoning, leading to improved design quality and creativity through a structured interaction paradigm.

Contribution

Introduces DesignerlyLoop, a novel interaction framework that explicitly separates design intent from LLM reasoning, facilitating better human-LLM alignment in creative design tasks.

Findings

Curated reasoning improves design quality and creativity.

Two-layer structure effectively separates design intent from LLM reasoning.

Study shows significant benefits of explicit reasoning inspection.

Abstract

Recent large language models (LLMs) show promise in design tasks, yet a fundamental misalignment persists: design thinking requires iterative intent formulation, while LLMs treat inputs as complete specifications. This challenges design intent formulation, where designers must progressively refine understanding through exploration. Existing tools either sacrifice exploratory flexibility for structural stability or leave reasoning implicit, failing to support human-LLM alignment. Through a formative study with eight designers, we introduce curated reasoning-enabling designers to explicitly inspect, reorganize, and selectively regenerate LLM reasoning structures. We present DesignerlyLoop, implementing this through a two-layer structure separating design intent from LLM reasoning. A study with 20 designers demonstrates that curated reasoning significantly improves design quality and creativity. Our work contributes a novel interaction paradigm for human-LLM alignment, transforming LLMs from content generators into structured reasoning partners in creative design.