Evaluating the Use of LLMs for Automated DOM-Level Resolution of Web Performance Issues

2026-01-09

arXiv.org

AI Summary

This study addresses the challenge of web performance optimization, which often requires complex DOM restructuring that developers struggle to perform efficiently under resource constraints. It presents the first systematic evaluation of nine state-of-the-art large language models (LLMs) in automatically generating DOM-level fixes for web performance issues, guided by real-world DOM structures and Lighthouse performance audit reports. Results show that LLMs excel at resolving SEO and accessibility problems, with GPT-4.1 reducing audit issues by 46.52%–48.68% on average across initial loading, interactivity, and network optimization categories. However, some models exhibit limited effectiveness, and certain repairs risk introducing visual stability regressions. The work reveals distinct strategic differences and inherent limitations of LLMs across various performance dimensions.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Evaluation and Analysis
• Application Domains: Web

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Users demand fast, seamless webpage experiences, yet developers often struggle to meet these expectations within tight constraints. Performance optimization, while critical, is a time-consuming and often manual process. One of the most complex tasks in this domain is modifying the Document Object Model (DOM), which is why this study focuses on it. Recent advances in Large Language Models (LLMs) offer a promising avenue to automate this complex task, potentially transforming how developers address web performance issues. This study evaluates the effectiveness of nine state-of-the-art LLMs for automated web performance issue resolution. For this purpose, we first extracted the DOM trees of 15 popular webpages (e.g., Facebook), and then we used Lighthouse to retrieve their performance audit reports. Subsequently, we passed the extracted DOM trees and corresponding audits to each model for resolution. Our study considers 7 unique audit categories, revealing that LLMs universally excel at SEO&Accessibility issues. However, their efficacy in performance-critical DOM manipulations is mixed. While high-performing models like GPT-4.1 delivered significant reductions in areas like Initial Load, Interactivity, and Network Optimization (e.g., 46.52% to 48.68% audit incidence reductions), others, such as GPT-4o-mini, notably underperformed, consistently. A further analysis of these modifications showed a predominant additive strategy and frequent positional changes, alongside regressions particularly impacting Visual Stability.

Problem

• LLMs
• DOM manipulation
• web performance
• automated resolution
• performance optimization

Innovation

• Large Language Models
• DOM manipulation
• Web performance optimization
• Lighthouse audits
• Automated code generation