TaskAudit: 通过代理任务执行检测移动应用中的功能性错误
TaskAudit: Detecting Functiona11ity Errors in Mobile Apps via Agentic Task Execution
AI总结：
TaskAudit通过代理任务执行检测移动应用中的功能性错误，识别出更多常见的可访问性问题。
摘要：
可访问性检查器是支持可访问性应用开发的工具，其使用受到可访问性最佳实践的鼓励。然而，大多数当前检查器评估静态或机械生成的上下文，无法捕捉影响移动应用功能的常见可访问性错误。在本工作中，我们定义功能性错误为仅通过交互（即，根据“功能”和“可访问性”的结合命名）才显现的可访问性障碍。我们介绍了TaskAudit，它包含三个组成部分：一个任务生成器，用于从应用屏幕生成交互任务；一个任务执行器，使用带有屏幕阅读器代理的代理来执行这些任务；以及一个可访问性分析器，通过分析交互痕迹来检测并报告可访问性错误。我们在真实世界应用上的评估显示，TaskAudit从54个应用屏幕中检测到48个功能性错误，而现有检查器则在4到20个之间。我们的分析展示了TaskAudit能够检测的常见错误模式，这些模式除了先前工作的结果外，还包括标签-功能不匹配、混乱的导航和不恰当的反馈。
英文摘要：
Accessibility checkers are tools in support of accessible app development, and their use is encouraged by accessibility best practices. However, most current checkers evaluate static or mechanically-generated contexts, failing to capture common accessibility errors impacting mobile app functionality. In this work, we define functiona11ity errors as accessibility barriers that only manifest through interaction (i.e., named according to a blend of "functionality" and "accessibility"). We introduce TaskAudit, which comprises three components: a Task Generator that constructs interactive tasks from app screens, a Task Executor that uses agents with a screen reader proxy to perform these tasks, and an Accessibility Analyzer that detects and reports accessibility errors by examining interaction traces. Our evaluation on real-world apps shows that TaskAudit detects 48 functiona11ity errors from 54 app screens, compared to between 4 and 20 with existing checkers. Our analysis demonstrates common error patterns that TaskAudit can detect in addition to those from prior work, including label-functionality mismatch, cluttered navigation, and inappropriate feedback.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
