Feature-Driven End-To-End Test Generation

TL;DR

AutoE2E leverages Large Language Models to automate the creation of feature-driven end-to-end web application tests, significantly improving coverage and coherence over existing methods.

Contribution

Introduces AutoE2E, a novel LLM-based approach for generating meaningful E2E tests, and E2EBench, a benchmark for assessing feature coverage of test suites.

Findings

AutoE2E achieves 79% feature coverage.

AutoE2E outperforms baselines by 558%.

Generated tests are more coherent and comprehensive.

Abstract

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. AutoE2E intelligently 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 AutoE2E achieves an average feature coverage of 79%, outperforming the best baseline by 558%, highlighting its effectiveness in generating high-quality, comprehensive test cases.