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

TL;DR

WebVIA introduces an interactive framework that automates UI-to-Code generation and validation, enabling the creation of executable, interactive web interfaces from design mockups with improved stability and accuracy.

Contribution

It is the first agentic framework for interactive UI-to-Code generation and validation, combining multi-state UI exploration, code generation, and interactivity verification.

Findings

WebVIA-Agent outperforms general-purpose agents in UI exploration stability.

Fine-tuned WebVIA-UI2Code models generate more executable and interactive code.

Significant improvements over baseline models on UI2Code benchmarks.

Abstract

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}}.