Paper page - Enabling Creative Exploration for Vibe Design Agents

Source: https://huggingface.co/papers/2609.15078

Abstract

Separating design exploration from code generation via structured intermediate specifications enables diverse UI alternatives without altering downstream generation settings.

Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent should do more than produce one valid page: it should help users explore coherent alternatives. Increasing token-level temperature is a blunt solution because it varies aesthetic decisions and syntax-sensitive code at the same time. We instead separate exploration from implementation through aninference architecturethat makes design direction an explicit intermediate decision. Inspired byVerbalized Sampling, a pre-pass proposes structureddesign specificationswithtypicality scores, an external selector samples one, and the downstream generator realizes the selected specification together with the original request under fixed settings. We apply this approach to UI themes andvisual-asset prompts. Across 168 prompts, with 1,255 paired comparisons per temperature for each intervention,theme samplingbroadens observed selection coverage and screenshot variation, while LLM-judge preferences vary across interventions, prompt complexity, and viewport. In an online experiment with more than 300,000 tasks, the observed code-export increase remains statistically uncertain, while fewer negative feedback events coexist with more correction interactions and modest operational costs. Together, these findings identify structureddesign specificationsas a practical control point for exploring alternative UI concepts while keeping downstream generation settings fixed.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2609\.15078

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.15078 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.15078 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.15078 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.