Ever-Improving Test Suite by Leveraging Large Language Models

April 15, 2025 Β· Declared Dead Β· πŸ› SIGSOFT FSE Companion

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Ketai Qiu arXiv ID 2506.11000 Category cs.SE: Software Engineering Citations 0 Venue SIGSOFT FSE Companion Last Checked 3 months ago
Abstract
Augmenting test suites with test cases that reflect the actual usage of the software system is extremely important to sustain the quality of long lasting software systems. In this paper, we propose E-Test, an approach that incrementally augments a test suite with test cases that exercise behaviors that emerge in production and that are not been tested yet. E-Test leverages Large Language Models to identify already-tested, not-yet-tested, and error-prone unit execution scenarios, and augment the test suite accordingly. Our experimental evaluation shows that E-Test outperforms the main state-of-the-art approaches to identify inadequately tested behaviors and optimize test suites.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted