一句话：提出基于 LLM 的分治式 Web 无障碍修复框架 A11YRepair，融合 WCAG 知识并构建 A11YBench 基准。
现有 Web 无障碍工具多止于检测违规，而通用 APR 系统在真实无障碍问题上效果不佳：无障碍违规常在同一页面成组出现，需跨文件协同修改，并依赖 WCAG 等领域规则，现有方法逐条独立修复，难以应对这种多故障规模。本文提出 A11YRepair，一个面向 Web 无障碍修复的 LLM 框架：先聚类需协同编辑的违规以减少冗余定位，再按根因分解每个簇，使 LLM 生成聚焦且一致的补丁，并在定位与合成阶段融入 WCAG 驱动知识。作者构建了包含 60 个 GitHub 真实 Web 项目的基准 A11YBench。实验显示其修复效果优于 SOTA 基线且成本更低，消融验证了分治设计与选择性领域知识的重要性，生成的补丁已被 Google、Microsoft、Facebook、IBM、K8s、Docker、Alibaba 等开源项目合并。
Web accessibility (A11Y), which ensures web content is perceivable and usable for users with disabilities, is a critical requirement for modern web applications. Yet existing tooling overwhelmingly focuses on detecting A11Y violations rather than repairing them. Automated program repair (APR) techniques appear promising for this setting, but our study shows that state-of-the-art APR systems perform poorly when applied to real-world A11Y violations. Unlike conventional sparse-bug scenarios, web A11Y issues often manifest as multiple structurally related violations per page, requiring coordinated edits across multiple files. Existing repair systems fail to manage this multi-fault scale, as they handle each bug individually without considering their relationships or incorporating domain rules such as the Web Content Accessibility Guidelines (WCAG). We propose A11YRepair, an LLM-based framework designed specifically for web A11Y repair. A11YRepair introduces a divide-and-conquer workflow that first clusters violations requiring coordinated edits to reduce redundant localization, and then decomposes each cluster by root cause so the LLM can generate focused and consistent patches. The framework further incorporates WCAG-driven knowledge to strengthen domain awareness during both fault localization and patch synthesis. To support systematic evaluation, we construct A11YBench, a benchmark of 60 real-world web projects collected from GitHub. Experimental results show that A11YRepair achieves higher repair effectiveness and lower cost than state-of-the-art baselines, and ablation studies confirm the importance of its divide-and-conquer design and selective domain knowledge integration. Specifically, patches generated by A11YRepair have been merged into open-source projects from Google, Microsoft, Facebook, IBM, K8s, Docker, and Alibaba, demonstrating its practical value in real-world dev scenarios. This work demonstrates the promise of LLM-driven accessibility repair and highlights the importance of combining structured repair strategies with domain expertise to advance inclusive software engineering.
@inproceedings{abs-2606-21926,
title = {A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer Repair},
author = {Kai Huang and Ling Zhu and Jian Zhang and Xiaofei Xie and Chunyang Chen},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834334}
}