Test Intention Guided LLM-Based Unit Test Generation

The emergence of Large Language Models (LLMs) has accelerated the progress of intelligent software engineering technologies, which brings promising possibilities for unit test generation. However, existing approaches for unit tests directly generated from Large Language Models (LLMs) often prove imp...

Full description

Saved in:
Bibliographic Details
Published inProceedings / International Conference on Software Engineering pp. 1026 - 1038
Main Authors Nan, Zifan, Guo, Zhaoqiang, Liu, Kui, Xia, Xin
Format Conference Proceeding
LanguageEnglish
Published IEEE 26.04.2025
Subjects
Industries
Java
Large language models
Life estimation
LLM
mocking
program analysis
Software engineering
test intention
Test pattern generators
unit test generation
Online AccessGet full text
ISSN1558-1225
DOI10.1109/ICSE55347.2025.00243

Cover

More Information
Summary:The emergence of Large Language Models (LLMs) has accelerated the progress of intelligent software engineering technologies, which brings promising possibilities for unit test generation. However, existing approaches for unit tests directly generated from Large Language Models (LLMs) often prove impractical due to their low coverage and insufficient mocking capabilities. This paper proposes IntUT, a novel approach that utilizes explicit test intentions (e.g., test inputs, mock behaviors, and expected results) to effectively guide the LLM to generate high-quality test cases. Our experimental results on three industry Java projects and live study demonstrate that prompting LLM with test intention can generate high-quality test cases for developers. Specifically, it achieves the improvements on branch coverage by 94 % and line coverage by 49 %. Finally, we obtain developers' feedback on using IntUT to generate cases for three new Java projects, achieving over 80 % line coverage and 30 % efficiency improvement on writing unit test cases.
ISSN:1558-1225
DOI:10.1109/ICSE55347.2025.00243