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

arXiv: https://arxiv.org/abs/2601.05502 · HTML: https://mlsanity.com/paper/2601.05502/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 67 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [WebFormer: The Web-page Transformer for Structure Information Extraction](https://mlsanity.com/paper/2202.00217/) (2022)
- [LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations](https://mlsanity.com/paper/2404.14459/) (2024)
- [Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?](https://mlsanity.com/paper/2210.14699/) (2022)
- [Improving web element localization by using a large language model](https://mlsanity.com/paper/2310.02046/) (2023)
- [Leveraging Large Language Models for Web Scraping](https://mlsanity.com/paper/2406.08246/) (2024)
- [Web Performance with Android's Battery-Saver Mode](https://mlsanity.com/paper/2003.06477/) (2020)
- [An Early Benchmark of Quality of Experience Between HTTP/2 and HTTP/3 using Lighthouse](https://mlsanity.com/paper/2004.01978/) (2020)

## Abstract (arXiv)

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.