Investigating Test Overfitting on SWE-bench

Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering 2026 Open access

Read full text
Authors: Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin J. Hirzel
DOI: 10.1145/3803437.3805574
Cited by: 0
References: 27

Abstract

Tests can be useful towards resolving issues on code repositories. However, relying too much on tests for issue resolution can lead to code that technically passes observed tests but actually misses important cases or even breaks functionality. This problem, called test overfitting, is exacerbated by the fact that issues usually lack readily executable tests. Instead, several issue resolution systems use tests auto-generated from issues, which may be imperfect. Some systems even iteratively refine code and tests jointly. This paper presents the first empirical study of test overfitting in this setting.

Fields of Study & Subjects

Software Testing and Debugging Techniques Software System Performance and Reliability Software Engineering Research

Publication details

Journal / source
Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering
Publisher
ACM
Pages
1292–1296
Publication date
5 July 2026