A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation

GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations (ICLR)

Original

Daya Guo, Shuo Ren, Shuai Lu, Long Zhou, Junjie Huang, Daxin Jiang, Shuming Shi, Huanbo Luan, and Ming Zhou. 2021 · 2009

Earlier work this paper cites.

Evaluating Large Language Models Trained on Code

OpenAI. 2021 · 2021

Earlier work this paper cites.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Original

Yue Wang, Weishi Wang, Shafiq Joty, and Steven C.H. Hoi. 2021 · 2021

Earlier work this paper cites.

Phind-CodeLlama

2023 · 2023

Earlier work this paper cites.

StarCoder 2 and The Stack v2: The Next Generation

Original

Anton Lozhko et al. 2024a · 2024

Earlier work this paper cites.

Mixtral of Experts

Original

Albert Q. Jiang et al. 2024b · 2024

Earlier work this paper cites.

ZEPHYR: DIRECT DISTILLATION OF LM ALIGNMENT

Original

Lewis Tunstall et al. 2024c · 2024

Earlier work this paper cites.

Deepseek-coder

Original

Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y.K. Li, Fuli Luo, Yingfei Xiong, and Wenfeng Liang. 2024 · 2024

Earlier work this paper cites.

A Unified Debugging Approach via LLM-Based Multi-Agent Synergy

Original

Cheryl Lee, Chunqiu Steven Xia, Jen tse Huang, Zhouruixin Zhu, Lingming Zhang, and Michael R. Lyu. 2024 · 2024

Earlier work this paper cites.

DEAR: A Novel Deep Learning-based Approach for Automated Program Repair

Yi Li, Shaohua Wang, and Tien N. Nguyen. 2024 · 2024

Cited alongside, same era.

Automatic Programming: Large Language Models and Beyond

Original

Michael R. Lyu, Baishakhi Ray, Abhik Roychoudhury, Shin Hwei Tan, and Patanamon Thongtanunam. 2024 · 2024

Cited alongside, same era.

How to Understand Whole Software Repository?

Original

Yingwei Ma, Qingping Yang, Rongyu Cao, Binhua Li, Fei Huang, and Yongbin Li. 2024 · 2024

Cited alongside, same era.

Large Language Model guided Protocol Fuzzing

Ruijie Meng, Martin Mirchev, Marcel Bohme, and Abhik Roychoudhury. 2024a · 2024

Cited alongside, same era.

Improving fault localization and program repair with deep semantic features and transferred knowledge

Xiangxin Meng, Xu Wang, Hongyu Zhang, Hailong Sun, and Xudong Liu. 2024b · 2024

Cited alongside, same era.

ProveNFix: Temporal Property-Guided Program Repair. In International Conference on Software Engineering (ICSE)

Yahui Song, Xiang Gao, Wenhua Li, Wei-Ngan Chin, and Abhik Roychoudhury. 2024 · 2024

Closest in time.

Evaluating Debugging Capability of Large Language Models

Original

Runchu Tian, Yining Ye, Yujia Qin, Xin Cong, Yankai Lin, Yinxu Pan, Yesai Wu, Haotian Hui, Weichuan Liu, Zhiyuan Liu, and Maosong Sun. 2024 · 2024

Closest in time.

Magicoder: Empowering Code Generation with OSS-Instruct

Original

Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang. 2024 · 2024

Closest in time.

Greybox Fuzzing for Concurrency Testing. In Proceedings of the 2024 ACM Conference on Computer and Communications Security (CCS)

Dylan Wolff, Zheng Shi, Gregory J. Duck, Umang Mathur, and Abhik Roychoudhury. 2024 · 2024

Closest in time.

WizardLM: Empowering Large Language Models to Follow Complex Instructions