一句话：利用LLM推断Web应用功能特征并生成可执行端到端测试，同时发布功能覆盖评测基准。
端到端（E2E）测试对保障Web应用质量至关重要，但手工编写耗时且现有自动生成技术产生的测试往往缺乏连贯性。本文提出 Autoe2e，一种借助大语言模型（LLM）自动化生成语义上有意义的、特征驱动E2E测试用例的新方法：它智能推断Web应用中潜在的功能特征，并将其转化为可执行的测试场景。针对社区缺乏评估手段的问题，作者还提出 E2EBENCH，一个可自动评估E2E测试套件功能覆盖率的基准。在 E2EBENCH 上的评估表明，Autoe2e 平均达到 79% 的功能覆盖率，相比最佳基线提升 558%，显示其在生成高质量、全面测试用例方面的有效性。
End-to-end (E2E) testing is essential for ensuring web application quality. However, manual test creation is time-consuming, and current test generation techniques produce incoherent tests. In this paper, we present Autoe2e,a novel approach that leverages Large Language Models (LLMs) to automate the generation of semantically meaningful feature-driven E2E test cases for web applications. Autoe2eintelligently infers potential features within a web application and translates them into executable test scenarios. Furthermore, we address a critical gap in the research community by introducing E2EBENCH, a new benchmark for automatically assessing the feature coverage of E2E test suites. Our evaluation on E2EBENCH demonstrates that Autoe2eachieves an average feature coverage of 79%, outperforming the best baseline by 558 %, highlighting its effectiveness in generating high-quality, comprehensive test cases.
DOI 原文 ·
@inproceedings{paperbot8718,
title = {Feature-Driven End-to-End Test Generation},
author = {Parsa Alian and Noor Nashid and Mobina Shahbandeh and Taha Shabani and Ali Mesbah},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00141}
}