Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage

Proceedings of the 23rd International Conference on Mining Software Repositories 2026 Open access

Read full text
Authors: Suzuka Yoshimoto, Shun FUJITA, Kosei Horikawa, Daniel Feitosa, Yutaro Kashiwa, Hajimu Iida
DOI: 10.1145/3793302.3793620
Cited by: 1
References: 22

Abstract

Agent-based coding tools have transformed software development practices. Unlike prompt-based approaches that require developers to manually integrate generated code, these agent-based tools autonomously interact with repositories to create, modify, and execute code, including test generation. While many developers have adopted agent-based coding tools, little is known about how these tools generate tests in real-world development scenarios or how AI-generated tests compare to human-written ones.

Publication details

Journal / source
Proceedings of the 23rd International Conference on Mining Software Repositories
Publisher
ACM
Pages
1014–1018
Publication date
13 April 2026