WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Mingde, Yang, Zhen, Hong, Wenyi, Pan, Lihang, Fan, Xinyue, Wang, Yan, Gu, Xiaotao, Xu, Bin, Tang, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914144070926336
author Xu, Mingde
Yang, Zhen
Hong, Wenyi
Pan, Lihang
Fan, Xinyue
Wang, Yan
Gu, Xiaotao
Xu, Bin
Tang, Jie
author_facet Xu, Mingde
Yang, Zhen
Hong, Wenyi
Pan, Lihang
Fan, Xinyue
Wang, Yan
Gu, Xiaotao
Xu, Bin
Tang, Jie
contents User interface (UI) development requires translating design mockups into functional code, a process that remains repetitive and labor-intensive. While recent Vision-Language Models (VLMs) automate UI-to-Code generation, they generate only static HTML/CSS/JavaScript layouts lacking interactivity. To address this, we propose WebVIA, the first agentic framework for interactive UI-to-Code generation and validation. The framework comprises three components: 1) an exploration agent to capture multi-state UI screenshots; 2) a UI2Code model that generates executable interactive code; 3) a validation module that verifies the interactivity. Experiments demonstrate that WebVIA-Agent achieves more stable and accurate UI exploration than general-purpose agents (e.g., Gemini-2.5-Pro). In addition, our fine-tuned WebVIA-UI2Code models exhibit substantial improvements in generating executable and interactive HTML/CSS/JavaScript code, outperforming their base counterparts across both interactive and static UI2Code benchmarks. Our code and models are available at \href{https://zheny2751-dotcom.github.io/webvia.github.io/}{\texttt{https://webvia.github.io}}.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06251
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation
Xu, Mingde
Yang, Zhen
Hong, Wenyi
Pan, Lihang
Fan, Xinyue
Wang, Yan
Gu, Xiaotao
Xu, Bin
Tang, Jie
Software Engineering
Artificial Intelligence
User interface (UI) development requires translating design mockups into functional code, a process that remains repetitive and labor-intensive. While recent Vision-Language Models (VLMs) automate UI-to-Code generation, they generate only static HTML/CSS/JavaScript layouts lacking interactivity. To address this, we propose WebVIA, the first agentic framework for interactive UI-to-Code generation and validation. The framework comprises three components: 1) an exploration agent to capture multi-state UI screenshots; 2) a UI2Code model that generates executable interactive code; 3) a validation module that verifies the interactivity. Experiments demonstrate that WebVIA-Agent achieves more stable and accurate UI exploration than general-purpose agents (e.g., Gemini-2.5-Pro). In addition, our fine-tuned WebVIA-UI2Code models exhibit substantial improvements in generating executable and interactive HTML/CSS/JavaScript code, outperforming their base counterparts across both interactive and static UI2Code benchmarks. Our code and models are available at \href{https://zheny2751-dotcom.github.io/webvia.github.io/}{\texttt{https://webvia.github.io}}.
title WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.06251