Agentic Web Accessibility Auditing: Authoring and Evaluating Per-Criterion Worker Agents for WCAG

2026-09-08

AI Summary

本文提出一个结合共享浏览器工具与特定标准工作代理的框架，实现WCAG 2.1和2.2部分标准的自动化网页可访问性评估，以提高准确性和证据收集。

Abstract

Automated accessibility assessments differ in the evidence they collect and the requirements they address. We present a framework that combines shared browser tools with criterion-specific worker agents, implementing 39 WCAG 2.1 Level A and AA criteria and one additional WCAG 2.2 criterion. We analyze archived predictions on 250 page-criterion records derived from professional audits of scholarly platforms. Workers recover 0.86 of positive reference labels, compared with 0.36 for axe-core and 0.67 for an uncued vision-language model, with lower precision. Criterion-level results, abstentions, development-exposure sensitivities, and separately instrumented runs qualify these comparisons. Inferred negative labels and differences between evaluated configurations limit conclusions about true accuracy and causal effects. We contribute the framework, its criterion-specific implementation, and an evaluation account that distinguishes detection, evidence availability, and resource use, motivating further study of inspectable automated assessments within professional auditing.

Problem

• web accessibility
• automated assessments
• WCAG
• evidence collection
• criterion-specific

Innovation

• Agentic Web Accessibility
• WCAG 2.1 and 2.2 Criteria
• Automated Assessments
• Criterion-Specific Worker Agents
• Professional Auditing