Automated program repair in the era of large pre-trained language models

CS Xia, Y Wei, L Zhang - 2023 IEEE/ACM 45th International …, 2023 - ieeexplore.ieee.org
Automated Program Repair (APR) aims to help developers automatically patch software
bugs. However, current state-of-the-art traditional and learning-based APR techniques face …

Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT

CS Xia, L Zhang - arXiv preprint arXiv:2304.00385, 2023 - arxiv.org
Automated Program Repair (APR) aims to automatically generate patches for buggy
programs. Recent APR work has been focused on leveraging modern Large Language …

Less training, more repairing please: revisiting automated program repair via zero-shot learning

CS Xia, L Zhang - Proceedings of the 30th ACM Joint European …, 2022 - dl.acm.org
Due to the promising future of Automated Program Repair (APR), researchers have
proposed various APR techniques, including heuristic-based, template-based, and …

Conversational automated program repair

CS Xia, L Zhang - arXiv preprint arXiv:2301.13246, 2023 - arxiv.org
Automated Program Repair (APR) can help developers automatically generate patches for
bugs. Due to the impressive performance obtained using Large Pre-Trained Language …

An extensive study on pre-trained models for program understanding and generation

Z Zeng, H Tan, H Zhang, J Li, Y Zhang… - Proceedings of the 31st …, 2022 - dl.acm.org
Automatic program understanding and generation techniques could significantly advance
the productivity of programmers and have been widely studied by academia and industry …

Baldur: Whole-proof generation and repair with large language models

E First, MN Rabe, T Ringer, Y Brun - Proceedings of the 31st ACM Joint …, 2023 - dl.acm.org
Formally verifying software is a highly desirable but labor-intensive task. Recent work has
developed methods to automate formal verification using proof assistants, such as Coq and …

Agentless: Demystifying llm-based software engineering agents

CS Xia, Y Deng, S Dunn, L Zhang - arXiv preprint arXiv:2407.01489, 2024 - arxiv.org
Recent advancements in large language models (LLMs) have significantly advanced the
automation of software development tasks, including code synthesis, program repair, and …

Evolving Paradigms in Automated Program Repair: Taxonomy, Challenges, and Opportunities

K Huang, Z Xu, S Yang, H Sun, X Li, Z Yan… - ACM Computing …, 2024 - dl.acm.org
With the rapid development and large-scale popularity of program software, modern society
increasingly relies on software systems. However, the problems exposed by software have …

A survey on machine learning techniques for source code analysis

T Sharma, M Kechagia, S Georgiou, R Tiwari… - arXiv preprint arXiv …, 2021 - arxiv.org
The advancements in machine learning techniques have encouraged researchers to apply
these techniques to a myriad of software engineering tasks that use source code analysis …

[HTML][HTML] A systematic mapping study of bug reproduction and localization

D Wang, M Galster, M Morales-Trujillo - Information and Software …, 2024 - Elsevier
Context: Identifying the root cause of a software bug and fixing it is challenging. One reason
for this is that many bugs are not reproducible during bug fixing. Objective: We aim to …