用LLM模拟真实用户人格提升移动应用功能覆盖测试
原标题：Towards Comprehensive Mobile Application Testing for User-centric Feature Coverage via Simulating Real-World Users with Personas
AI 摘要
该论文针对LLM智能体黑盒移动应用测试中现有指标（Activity Coverage）无法衡量用户真正关心功能覆盖的问题，提出用户中心功能覆盖基准（含3,012个来自应用描述与真实评论的目标功能及LLM-as-a-judge自动评估流程），并设计ECS框架，通过探索、关键用户旅程（CUJ）与人格增强的合成评论来模拟真实用户。ECS实现64.1%功能覆盖率，较最先进基线提升23.8%，并覆盖应用描述中72.5%的功能。失败分析指出无状态性和探索可发现性是主要失败原因。
正文节选
Towards Comprehensive Mobile Application Testing for User-centric Feature Coverage via Simulating Real-World Users with Personas Abstract Large Language Model (LLM) agents are increasingly used for black-box mobile application testing, where the ultimate goal is the comprehensive coverage of the features users rely on. However, most existing studies focus on Activity Coverage, which measures the proportion of distinct application screens visited during a test session but does not directly measur