In a head-to-head test, Gemini detected test smells most consistently across Python and Java, but LLM-based refactoring frequently reduced test coverage and could introduce new smells.
When and why your code starts to smell bad,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Evaluating LLMs Effectiveness in Detecting and Correcting Test Smells: An Empirical Study
In a head-to-head test, Gemini detected test smells most consistently across Python and Java, but LLM-based refactoring frequently reduced test coverage and could introduce new smells.