GuidedFewShot prompts embedding a mutation taxonomy achieve the highest single-run failure-mode coverage in LLM-generated robustness tests for microservices, with prompt strategy explaining more diversity variation than model size.
Leveraging large language models to improve REST API testing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-Based Robustness Testing of Microservice Applications: An Empirical Study
GuidedFewShot prompts embedding a mutation taxonomy achieve the highest single-run failure-mode coverage in LLM-generated robustness tests for microservices, with prompt strategy explaining more diversity variation than model size.