# Enabling Creative Exploration for Vibe Design Agents

arXiv: https://arxiv.org/abs/2609.15078 · HTML: https://mlsanity.com/paper/2609.15078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 30 of 32)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset](https://mlsanity.com/paper/2403.09029/) (2024)
- [pix2code: Generating Code from a Graphical User Interface Screenshot](https://mlsanity.com/paper/1705.07962/) (2017)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs](https://mlsanity.com/paper/2406.20098/) (2024)
- [On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization](https://mlsanity.com/paper/2405.16455/) (2024)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping](https://mlsanity.com/paper/2411.03292/) (2024)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [Prompting is not a substitute for probability measurements in large language models](https://mlsanity.com/paper/2305.13264/) (2023)
- [WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs](https://mlsanity.com/paper/2404.06369/) (2024)
- [Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots](https://mlsanity.com/paper/2109.08763/) (2021)
- [FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow](https://mlsanity.com/paper/2505.17399/) (2025)
- [UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback](https://mlsanity.com/paper/2406.07739/) (2024)
- [MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designs](https://mlsanity.com/paper/2412.15310/) (2024)
- [UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs](https://mlsanity.com/paper/2505.09904/) (2025)
- [FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation](https://mlsanity.com/paper/2506.13832/) (2025)
- [Calibrating Verbalized Probabilities for Large Language Models](https://mlsanity.com/paper/2410.06707/) (2024)
- [Misty: UI Prototyping Through Interactive Conceptual Blending](https://mlsanity.com/paper/2409.13900/) (2024)
- [Asking a Language Model for Diverse Responses](https://mlsanity.com/paper/2509.17570/) (2025)
- [MAxPrototyper: A Multi-Agent Generation System for Interactive User Interface Prototyping](https://mlsanity.com/paper/2405.07131/) (2024)
- [DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models](https://mlsanity.com/paper/2411.01606/) (2024)
- [EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation](https://mlsanity.com/paper/2509.12159/) (2025)
- [ComUICoder: Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Element-wise Feedback](https://mlsanity.com/paper/2602.19276/) (2026)
- [Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitions](https://mlsanity.com/paper/2408.00778/) (2024)

## Abstract (arXiv)

Vibe design agents translate natural-language requests into interfaces, yet repeated generations often converge on similar visual directions. We present an inference architecture that makes design exploration an explicit stage before implementation. A pre-pass proposes structured design specifications with typicality weights, an external policy samples a direction, and the generator implements it under fixed decoding settings. Candidate elicitation draws on Verbalized Sampling. Applied to UI themes and visual-asset prompts, this architecture provides direct control over aesthetic exploration without changing code-generation temperature. Across 168 benchmark prompts, theme sampling expands observed selection coverage from one option to nearly three and increases rendered visual variation. For visual-asset prompts, the strongest observed LLM-judge win/loss ratio is 1.32, with only a small change in whole-screen similarity. Localized aesthetic choices can thus influence judged preference even when the overall screen remains similar. We further evaluate joint theme and asset sampling in a randomized online study conducted over nearly two months, covering 3.39 million tasks and 87,416 labeled conversations. These studies show how explicit design specifications support exploration of alternative UI concepts and help us evaluate their effects on rendered interfaces, judged preference, and user interaction.