Human-competitive Patches in Automatic Program Repair with Repairnator

10/13/2018
by   Martin Monperrus, et al.
0

Repairnator is a bot. It constantly monitors software bugs discovered during continuous integration of open-source software and tries to fix them automatically. If it succeeds to synthesize a valid patch, Repairnator proposes the patch to the human developers, disguised under a fake human identity. To date, Repairnator has been able to produce 5 patches that were accepted by the human developers and permanently merged in the code base. This is a milestone for human-competitiveness in software engineering research on automatic program repair.

READ FULL TEXT

page 1

page 2

page 3

research
10/11/2019

Repairnator patches programs automatically

Repairnator is a bot. It constantly monitors software bugs discovered du...
research
11/24/2018

How to Design a Program Repair Bot? Insights from the Repairnator Project

Program repair research has made tremendous progress over the last few y...
research
09/01/2023

Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair

During Automated Program Repair (APR), it can be challenging to synthesi...
research
07/02/2018

Automatic Software Repair: a Bibliography

This article presents a survey on automatic software repair. Automatic s...
research
04/05/2023

Explainable Automated Debugging via Large Language Model-driven Scientific Debugging

Automated debugging techniques have the potential to reduce developer ef...
research
07/15/2019

Characterizing Developer Use of Automatically Generated Patches

We present a study that characterizes the way developers use automatical...
research
05/12/2023

Where to Look When Repairing Code? Comparing the Attention of Neural Models and Developers

Neural network-based techniques for automated program repair are becomin...

Please sign up or login with your details

Forgot password? Click here to reset