2026-05-27T05:32:46Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/408162026-02-03T11:47:41Zcom_10630_2254col_10630_37959

Lenke, David Ferrer-Urbano, Francisco Javier Chicano-García, José-Francisco 2025-11-19T09:49:38Z 2025-11-19T09:49:38Z 2025 https://hdl.handle.net/10630/40816 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 still struggle 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 and four 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 industrial software, 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 further reduce costs. eng open access Aprendizaje automático (Inteligencia artificial) Lenguajes de programación Proceso en lenguaje natural (Informática) Influence of External Dependency Retrieval and Prompt Engineering in Test Case Generation using LLMs conference output