Mokav: Execution-driven differential testing with LLMs
Authors:
- Khashayar EtemadiKEKhashayar Etemadi
- Bardia MohammadiBMBardia Mohammadi
- Zhendong SuZSZhendong Su
- Martin MonperrusMMMartin Monperrus
- 19 July 2025
- journal article
- Published by Elsevier in Journal of Systems and Software
- Vol. 230
Abstract
No abstract availableAll Related Versions
Funding Information
- Knut och Alice Wallenbergs Stiftelse
This publication has 38 references indexed in Scilit:
- How secure is AI-generated code: a large-scale comparison of large language modelsEmpirical Software Engineering, 2024
- Effective test generation using pre-trained Large Language Models and mutation testingInformation and Software Technology, 2024
- ChatGPT vs SBST: A Comparative Assessment of Unit Test Suite GenerationIEEE Transactions on Software Engineering, 2024
- Augmenting Diffs With Runtime InformationIEEE Transactions on Software Engineering, 2023
- An empirical study of automated unit test generation for PythonEmpirical Software Engineering, 2023
- Duo: Differential Fuzzing for Deep Learning OperatorsIEEE Transactions on Reliability, 2021
- A systematic literature review of techniques and metrics to reduce the cost of mutation testingJournal of Systems and Software, 2019
- Code4Bench: A multidimensional benchmark of Codeforces data for different program analysis techniquesJournal of Computer Languages, 2019
- Automated Test Case Generation as a Many-Objective Optimisation Problem with Dynamic Selection of the TargetsIEEE Transactions on Software Engineering, 2017
- Differential testing2007