A web test case repair approach based on test intent

Web test case automatic repair technology plays a crucial role in the maintenance of web application test suites. As web applications are frequently updated, changes may introduce web elements in new versions, causing test cases to fail. A major issue with existing methods is the lack of effective representation of the test intent and analysis of the reasons for failure, resulting in a failure to guide and assist in test case repair at a macro level. This makes it impossible to effectively repair broken test cases caused by test flow changes or propagated breakages. Empirical analysis shows that test intent and causes of failure are very useful for test case repair. This paper proposes a test intent-driven web test repair approach named LetTe (guiding LLM to fix Web UI tests based on test intent), which first parses the test intent and failure reasons of broken web test cases, and then guides the large language model (LLM) to fix them via prompt design and fine-tuning. LetTe’s repair logic simulates that of a human expert—given the test intent and reasons for failure, “ think about” possible repair plans and then generates repair candidates via the corresponding chain-of-thought. This paper evaluates LetTe across seven Web applications collected from open-source websites and publicly available datasets. The experimental results show that our approach achieves a 75% correct repair rate, which is higher than that of all baseline methods.