1 code implementation • 13 Dec 2023 • June Sallou, Thomas Durieux, Annibale Panichella
Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization.
3 code implementations • 28 May 2019 • Thomas Durieux, Fernanda Madeiral, Matias Martinez, Rui Abreu
Our goal is to have a better understanding of the current state of automatic program repair tools on a large diversity of benchmarks.
Software Engineering
1 code implementation • 22 May 2019 • Thomas Durieux, Rui Abreu
Benchmarks play an important role in evaluating the efficiency and effectiveness of solutions to automate several phases of the software development lifecycle.
Software Engineering
2 code implementations • 13 Oct 2018 • Martin Monperrus, Simon Urli, Thomas Durieux, Matias Martinez, Benoit Baudry, Lionel Seinturier
Repairnator is a bot.
Software Engineering
2 code implementations • 30 Jul 2018 • Fernanda Madeiral, Thomas Durieux, Victor Sobreira, Marcelo Maia
The characterization of bug datasets is essential to support the evaluation of automatic program repair tools.
Software Engineering
2 code implementations • 25 Oct 2017 • Thomas Durieux, Youssef Hamadi, Zhongxing Yu, Benoit Baudry, Martin Monperrus
In this paper, we study, design and perform an experiment that analyzes the size and the diversity of the failure-oblivious behaviors.
Software Engineering
1 code implementation • 26 May 2015 • Matias Martinez, Thomas Durieux, Jifeng Xuan, Romain Sommerard, Martin Monperrus
The result of our experiment shows that 47 bugs of the Defects4J dataset can be automatically repaired by state-of- the-art repair.
Software Engineering