RT Conference Proceedings
T1 Influence of External Dependency Retrieval and Prompt Engineering in Test Case Generation using LLMs
A1 Lenke, David
A1 Ferrer-Urbano, Francisco Javier
A1 Chicano-García, José-Francisco
K1 Aprendizaje automático (Inteligencia artificial)
K1 Lenguajes de programación
K1 Proceso en lenguaje natural (Informática)
AB The recent rise of large language models (LLMs) has enabled the generation of higher-quality test cases by leveraging the semantics of the methods under test. However, existing LLM-based approaches stillstruggle to achieve high coverage levels. To mitigate this issue, we present two complementary techniques in this work: Prompt Engineering and External Dependency Retrieval for context enrichment. We evaluated our improvements through an ablation study on three open-source andfour proprietary projects, encompassing 261 distinct methods. For each method, we generated test suites under four implementations and performed ten independent runs, yielding a total of 10,440 executions. Our combined approach yields an average coverage increase of 12% on industrialsoftware, with statistically significant gains over all other variants studied in this paper. Although our enhancements increase the context (the number of input tokens rises by 66.3%), this is partially compensated by a reduction in output tokens due to fewer repair attempts, so that the overall cost overhead remains moderate at about 16%. As future work, we aim to identify the minimal necessary context that still yields significant improvements in test coverage, which could help to furtherreduce costs.
YR 2025
FD 2025
LK https://hdl.handle.net/10630/40816
UL https://hdl.handle.net/10630/40816
LA eng
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026