Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ahmed, Toufique, Ganhotra, Jatin, Shinnar, Avraham, Hirzel, Martin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914274206547968
author Ahmed, Toufique
Ganhotra, Jatin
Shinnar, Avraham
Hirzel, Martin
author_facet Ahmed, Toufique
Ganhotra, Jatin
Shinnar, Avraham
Hirzel, Martin
contents A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically. The primary challenge in this setting is that the code to be tested is either missing or wrong, as evidenced by the existence of the issue in the first place. This has held back test generation for this setting: without the correct code to execute, it is difficult to leverage execution feedback to generate good tests. This paper introduces novel techniques for leveraging execution feedback to get around this problem, implemented in a new reproduction test generator called e-Otter++. Experiments show that e-Otter++ represents a leap ahead in the state-of-the-art for this problem, generating tests with an average fail-to-pass rate of 63% on the TDD-Bench Verified benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06365
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection
Ahmed, Toufique
Ganhotra, Jatin
Shinnar, Avraham
Hirzel, Martin
Software Engineering
A software engineering issue (SWE issue) is easier to resolve when accompanied by a reproduction test. Unfortunately, most issues do not come with functioning reproduction tests, so this paper explores how to generate them automatically. The primary challenge in this setting is that the code to be tested is either missing or wrong, as evidenced by the existence of the issue in the first place. This has held back test generation for this setting: without the correct code to execute, it is difficult to leverage execution feedback to generate good tests. This paper introduces novel techniques for leveraging execution feedback to get around this problem, implemented in a new reproduction test generator called e-Otter++. Experiments show that e-Otter++ represents a leap ahead in the state-of-the-art for this problem, generating tests with an average fail-to-pass rate of 63% on the TDD-Bench Verified benchmark.
title Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection
topic Software Engineering
url https://arxiv.org/abs/2508.06365