2024

CodeAgent: Autonomous Communicative Agents for Code Review

Tang, Xunzhu, Kim, Kisub, Song, Yewei et al.

Understand

Code review, which aims at ensuring the overall quality and reliability of software, is a cornerstone of software development.

Unfortunately, while crucial, Code review is a labor-intensive process that the research community is looking to automate.
Existing automated methods rely on single input-output generative models and thus generally struggle to emulate the collaborative nature of code review.
This work introduces \tool{}, a novel multi-agent Large Language Model (LLM) system for code review automation.

Built on

Expectations, outcomes, and challenges of modern code review
Alberto Bacchelli and Christian Bird. 2013 · 2013
Earlier work this paper cites.
Impact of peer code review on peer impression formation: A survey
Amiangshu Bosu and Jeffrey C Carver. 2013 · 2013
Earlier work this paper cites.
A review on evaluation metrics for data classification evaluations
Mohammad Hossin and Md Nasir Sulaiman. 2015 · 2015
Earlier work this paper cites.
Codebert: A pre-trained model for programming and natural languages
Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, and Ming Zhou. 2020 · 2020
Earlier work this paper cites.
Does code review really remove coding convention violations?
DongGyun Han, Chaiyong Ragkhitwetsagul, Jens Krinke, Matheus Paixao, and Giovanni Rosa. 2020 · 2020
Earlier work this paper cites.
Core: Automating review recommendation for code changes
Jing Kai Siow, Cuiyun Gao, Lingling Fan, Sen Chen, and Yang Liu. 2020 · 2020
Earlier work this paper cites.
Using machine learning to identify code fragments for manual review
Miroslaw Staron, Mirosław Ochodek, Wilhelm Meding, and Ola Söder. 2020 · 2020
Earlier work this paper cites.
Deep learning based vulnerability detection: Are we there yet?
Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, and Baishakhi Ray. 2021 · 2021
Earlier work this paper cites.
A systematic literature review and taxonomy of modern code review
Nicole Davila and Ingrid Nunes. 2021 · 2021
Earlier work this paper cites.
NL-EDIT: Correcting semantic parse errors through natural language interaction
Ahmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, and Ahmed Hassan Awadallah. 2021 · 2021
Earlier work this paper cites.
Graphcodebert: Pre-training code representations with data flow
Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin B. Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2021 · 2021
Earlier work this paper cites.
Towards automating code review at scale
Vincent J Hellendoorn, Jason Tsay, Manisha Mukherjee, and Martin Hirzel. 2021 · 2021
Earlier work this paper cites.
Deep just-in-time inconsistency detection between comments and source code
Sheena Panthaplackel, Junyi Jessy Li, Milos Gligoric, and Raymond J Mooney. 2021 · 2021
Earlier work this paper cites.
Towards automating code review activities
Rosalia Tufano, Luca Pascarella, Michele Tufano, Denys Poshyvanyk, and Gabriele Bavota. 2021 · 2021
Earlier work this paper cites.
Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation
Yue Wang, Weishi Wang, Shafiq R. Joty, and Steven C. H. Hoi. 2021 · 2021
Earlier work this paper cites.
Less is more: supporting developers in vulnerability detection during code review
Larissa Braz, Christian Aeberhard, Gül Çalikli, and Alberto Bacchelli. 2022 · 2022
Earlier work this paper cites.
Aligning offline metrics and human judgments of value of ai-pair programmers
Original
Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu, and Saleema Amershi. 2022 · 2022
Earlier work this paper cites.

Similar

Commentfinder: a simpler, faster, more accurate code review comments recommendation
Yang Hong, Chakkrit Tantithamthavorn, Patanamon Thongtanunam, and Aldeida Aleti. 2022 · 2022
Cited alongside, same era.
Codereviewer: Pre-training for automating code review activities
Zhiyu Li, Shuai Lu, Daya Guo, Nan Duan, Shailesh Jannu, Grant Jenks, Deep Majumder, Jared Green, Alexey Svyatkovskiy, Shengyu Fu, et al. 2022 · 2022
Cited alongside, same era.
Chatgpt
OPENAI. 2022 · 2022
Cited alongside, same era.
Autotransform: Automated code transformation to support modern code review process
Patanamon Thongtanunam, Chanathip Pornprasit, and Chakkrit Tantithamthavorn. 2022 · 2022
Cited alongside, same era.
Is this change the answer to that problem? correlating descriptions of bug and code changes for evaluating patch correctness
Original
Haoye Tian, Xunzhu Tang, Andrew Habib, Shangwen Wang, Kui Liu, Xin Xia, Jacques Klein, and Tegawendé F Bissyandé. 2022 · 2022
Cited alongside, same era.
Using pre-trained models to boost code review automation
Rosalia Tufano, Simone Masiero, Antonio Mastropaolo, Luca Pascarella, Denys Poshyvanyk, and Gabriele Bavota. 2022 · 2022
Cited alongside, same era.
A systematic literature review on the use of deep learning in software engineering research
Cody Watson, Nathan Cooper, David Nader Palacio, Kevin Moran, and Denys Poshyvanyk. 2022 · 2022
Cited alongside, same era.
Chain-of-thought prompting elicits reasoning in large language models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022 · 2022
Cited alongside, same era.
React: Synergizing reasoning and acting in language models
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022 · 2022
Cited alongside, same era.
Consistent or not? an investigation of using pull request template in github
Mengxi Zhang, Huaxiao Liu, Chunyang Chen, Yuzhou Liu, and Shuotong Bai. 2022 · 2022
Cited alongside, same era.
Playing repeated games with large language models
Elif Akata, Lion Schulz, Julian Coda-Forno, Seong Joon Oh, Matthias Bethge, and Eric Schulz. 2023 · 2023
Cited alongside, same era.
Large language models as tool makers
Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, and Denny Zhou. 2023 · 2023
Cited alongside, same era.

Then

Metagpt: Meta programming for multi-agent collaborative framework
Original
Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, et al. 2023 · 2023
Later among the works it cites.
Encouraging divergent thinking in large language models through multi-agent debate
Original
Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, and Shuming Shi. 2023 · 2023
Later among the works it cites.
Llama-reviewer: Advancing code review automation with large language models through parameter-efficient fine-tuning
Junyi Lu, Lei Yu, Xiaojia Li, Li Yang, and Chun Zuo. 2023 · 2023
Later among the works it cites.
A systematic literature review on the impact of formatting elements on code legibility
Delano Oliveira, Reydne Santos, Fernanda Madeiral, Hidehiko Masuhara, and Fernando Castor. 2023 · 2023
Later among the works it cites.
Generative agents: Interactive simulacra of human behavior
Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023 · 2023
Later among the works it cites.
Communicative agents for software development
Original
Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. 2023 · 2023
Later among the works it cites.
Multi-agent collaboration: Harnessing the power of intelligent llm agents
Yashar Talebirad and Amirhossein Nadiri. 2023 · 2023
Later among the works it cites.
Just-in-time security patch detection–llm at the rescue for data augmentation
Original
Xunzhu Tang, Zhenghan Chen, Kisub Kim, Haoye Tian, Saad Ezzini, and Jacques Klein. 2023 · 2023
Later among the works it cites.
Is chatgpt the ultimate programming assistant–how far is it?
Original
Haoye Tian, Weiqi Lu, Tsz On Li, Xunzhu Tang, Shing-Chi Cheung, Jacques Klein, and Tegawendé F Bissyandé. 2023 · 2023
Later among the works it cites.
Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration
Original
Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. 2023 · 2023
Later among the works it cites.
Multi-party chat: Conversational agents in group settings with humans and models
Jimmy Wei, Kurt Shuster, Arthur Szlam, Jason Weston, Jack Urbanek, and Mojtaba Komeili. 2023 · 2023
Later among the works it cites.
The rise and potential of large language model based agents: A survey
Original
Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2023 · 2023
Later among the works it cites.
Building cooperative embodied agents modularly with large language models
Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B Tenenbaum, Tianmin Shu, and Chuang Gan. 2023 · 2023
Later among the works it cites.
Generation-based code review automation: How far are we?
Original
Xin Zhou, Kisub Kim, Bowen Xu, DongGyun Han, Junda He, and David Lo. 2023 · 2023
Later among the works it cites.
Autocoderover: Autonomous program improvement
Original
Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury. 2024 · 2024
Closest in time.
Neo-bench: Evaluating robustness of large language models with neologisms
Original
Jonathan Zheng, Alan Ritter, and Wei Xu. 2024 · 2024
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…