# UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback

arXiv: https://arxiv.org/abs/2406.07739 · HTML: https://mlsanity.com/paper/2406.07739/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators](https://mlsanity.com/paper/1901.06767/) (2019)
- [Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning](https://mlsanity.com/paper/2108.03353/) (2021)
- [Attribute-conditioned Layout GAN for Automatic Graphic Design](https://mlsanity.com/paper/2009.05284/) (2020)
- [Screen Recognition: Creating Accessibility Metadata for Mobile Applications from Pixels](https://mlsanity.com/paper/2101.04893/) (2021)
- [WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics](https://mlsanity.com/paper/2301.13280/) (2023)
- [On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages](https://mlsanity.com/paper/2204.09653/) (2022)
- [PLay: Parametrically Conditioned Layout Generation using Latent Diffusion](https://mlsanity.com/paper/2301.11529/) (2023)
- [Scout: Rapid Exploration of Interface Layout Alternatives through High-Level Design Constraints](https://mlsanity.com/paper/2001.05424/) (2020)
- [Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders](https://mlsanity.com/paper/2001.05308/) (2020)

## Built on by (most cited first, 27 of 27)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding](https://mlsanity.com/paper/2510.11498/) (2025)
- [From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts](https://mlsanity.com/paper/2410.09006/) (2024)
- [VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation](https://mlsanity.com/paper/2602.05998/) (2026)
- [AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design](https://mlsanity.com/paper/2608.13560/) (2026)
- [DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation](https://mlsanity.com/paper/2410.00201/) (2024)
- [DesignPref: Capturing Personal Preferences in Visual Design Generation](https://mlsanity.com/paper/2511.20513/) (2025)
- [Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning](https://mlsanity.com/paper/2504.01911/) (2025)
- [DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces](https://mlsanity.com/paper/2509.13444/) (2025)
- [WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing](https://mlsanity.com/paper/2603.25226/) (2026)
- [Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitions](https://mlsanity.com/paper/2408.00778/) (2024)
- [Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming](https://mlsanity.com/paper/2503.14488/) (2025)
- [Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding](https://mlsanity.com/paper/2505.05026/) (2025)
- [Improving User Interface Generation Models from Designer Feedback](https://mlsanity.com/paper/2509.16779/) (2025)
- [Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation](https://mlsanity.com/paper/2608.24138/) (2026)
- [1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World](https://mlsanity.com/paper/2602.18548/) (2026)
- [UXBench: Measuring the Actionability of LLM-Generated UX Critiques](https://mlsanity.com/paper/2606.16262/) (2026)
- [ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow](https://mlsanity.com/paper/2502.03330/) (2025)
- [When Discourse Stalls: Moving Past Five Semantic Stopsigns about Generative AI in Design Research](https://mlsanity.com/paper/2503.08565/) (2025)
- [LikeThis! Empowering App Users to Submit UI Improvement Suggestions Instead of Complaints](https://mlsanity.com/paper/2603.04245/) (2026)
- [Efficient Personalization of Generative User Interfaces](https://mlsanity.com/paper/2604.09876/) (2026)
- [Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation](https://mlsanity.com/paper/2608.03691/) (2026)
- [LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages](https://mlsanity.com/paper/2608.27902/) (2026)
- [The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents](https://mlsanity.com/paper/2608.28795/) (2026)
- [Enabling Creative Exploration for Vibe Design Agents](https://mlsanity.com/paper/2609.15078/) (2026)
- [TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity](https://mlsanity.com/paper/2610.10374/) (2026)
- [Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution](https://mlsanity.com/paper/2610.20100/) (2026)

## Abstract (arXiv)

Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely on expensive human feedback or distilling a proprietary model. In this paper, we explore the use of automated feedback (compilers and multi-modal models) to guide LLMs to generate high-quality UI code. Our method starts with an existing LLM and iteratively produces improved models by self-generating a large synthetic dataset using an original model, applying automated tools to aggressively filter, score, and de-duplicate the data into a refined higher quality dataset. The original LLM is improved by finetuning on this refined dataset. We applied our approach to several open-source LLMs and compared the resulting performance to baseline models with both automated metrics and human preferences. Our evaluation shows the resulting models outperform all other downloadable baselines and approach the performance of larger proprietary models.