MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

Forum topic · 小凯 · 2026-04-18

Summary

MM-WebAgent (arXiv:2504.13095) is a hierarchical agentic framework for multimodal webpage generation, developed by Yan Li, Zezi Zeng, and Yifan Yang. While AI-generated content (AIGC) tools make it easy to create images, videos, and visualizations for webpage design, integrating them directly into automated webpage generation often produces style inconsistency and poor global coherence because elements are generated in isolation. MM-WebAgent addresses this by coordinating AIGC-based element generation through hierarchical planning and iterative self-reflection, jointly optimizing global layout, local multimodal content, and their integration to produce coherent, visually consistent webpages. The authors also introduce a multimodal webpage generation benchmark with a multi-level evaluation protocol for systematic assessment. Experiments show MM-WebAgent outperforms code-generation and agent-based baselines, particularly in multimodal element generation and integration. Code and data are available at https://aka.ms/mm-webagent.

Paper Overview

Field: NLP Authors: Yan Li, Zezi Zeng, Yifan Yang Published: 2025-04-17 arXiv: 2504.13095

Abstract

The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visualizations to be created on demand for webpage design, offering a flexible and increasingly adopted paradigm for modern UI/UX. However, directly integrating such tools into automated webpage generation often leads to style inconsistency and poor global coherence, as elements are generated in isolation.

MM-WebAgent is a hierarchical agentic framework for multimodal webpage generation that coordinates AIGC-based element generation through hierarchical planning and iterative self-reflection. It jointly optimizes global layout, local multimodal content, and their integration, producing coherent and visually consistent webpages.

Key Contributions

A hierarchical agentic framework combining hierarchical planning with iterative self-reflection to coordinate AIGC element generation
Joint optimization of global layout, local multimodal content, and their integration
A new benchmark for multimodal webpage generation with a multi-level evaluation protocol

Results

Experiments show that MM-WebAgent outperforms code-generation and agent-based baselines, especially in multimodal element generation and integration.

Code and data: https://aka.ms/mm-webagent