2024

MarsCode Agent: AI-native Automated Bug Fixing

Liu, Yizhou, Gao, Pengfei, Wang, Xinchen et al.

Understand

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing.

However, the application of LLMs for automated bug fixing remains challenging due to the complexity and diversity of real-world software systems.
In this paper, we introduce MarsCode Agent, a novel framework that leverages LLMs to automatically identify and repair bugs in software code.
MarsCode Agent combines the power of LLMs with advanced code analysis techniques to accurately localize faults and generate patches.

Built on

On the accuracy of spectrum-based fault localization
Rui Abreu, Peter Zoeteweij, and Arjan JC Van Gemund · 2007
Earlier work this paper cites.
A practical evaluation of spectrum-based fault localization
Rui Abreu, Peter Zoeteweij, Rob Golsteijn, and Arjan JC Van Gemund · 2009
Earlier work this paper cites.
Genprog: A generic method for automatic software repair
Claire Le Goues, ThanhVu Nguyen, Stephanie Forrest, and Westley Weimer · 2011
Earlier work this paper cites.
Semfix: Program repair via semantic analysis
Hoang Duong Thien Nguyen, Dawei Qi, Abhik Roychoudhury, and Satish Chandra · 2013
Earlier work this paper cites.
Slice-based statistical fault localization
Xiaoguang Mao, Yan Lei, Ziying Dai, Yuhua Qi, and Chengsong Wang · 2014
Earlier work this paper cites.
Metallaxis-fl: mutation-based fault localization
Mike Papadakis and Yves Le Traon · 2015
Earlier work this paper cites.
Empirical study on synthesis engines for semantics-based program repair
Xuan-Bach D Le, David Lo, and Claire Le Goues · 2016
Earlier work this paper cites.
A survey on software fault localization
W Eric Wong, Ruizhi Gao, Yihao Li, Rui Abreu, and Franz Wotawa · 2016
Earlier work this paper cites.
Jfix: semantics-based repair of java programs via symbolic pathfinder
Xuan-Bach D Le, Duc-Hiep Chu, David Lo, Claire Le Goues, and Willem Visser · 2017
Earlier work this paper cites.
Improving spectral-based fault localization using static analysis
Neelofar Neelofar, Lee Naish, Jason Lee, and Kotagiri Ramamohanarao · 2017
Earlier work this paper cites.
Accelerating search-based program repair
Ben Mehne, Hiroaki Yoshida, Mukul R Prasad, Koushik Sen, Divya Gopinath, and Sarfraz Khurshid · 2018
Earlier work this paper cites.
Precise learn-to-rank fault localization using dynamic and static features of target programs
Yunho Kim, Seokhyeon Mun, Shin Yoo, and Moonzoo Kim · 2019
Earlier work this paper cites.
Automated program repair
Claire Le Goues, Michael Pradel, and Abhik Roychoudhury · 2019
Earlier work this paper cites.
Codebert: A pre-trained model for programming and natural languages
Original
Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, et al · 2020
Earlier work this paper cites.
Dlfix: Context-based code transformation learning for automated program repair
Yi Li, Shaohua Wang, and Tien N Nguyen · 2020
Earlier work this paper cites.
Evaluating large language models trained on code
Original
Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al · 2021
Earlier work this paper cites.
Albfl: A novel neural ranking model for software fault localization via combining static and dynamic features
Xi Xiao, Yuqing Pan, Bin Zhang, Guangwu Hu, Qing Li, and Runiu Lu · 2021
Earlier work this paper cites.
Improving search-based automatic program repair with neural machine translation
Dongcheng Li, W Eric Wong, Mingyong Jian, Yi Geng, and Matthew Chau · 2022
Earlier work this paper cites.

Similar

Dear: A novel deep learning-based approach for automated program repair
Yi Li, Shaohua Wang, and Tien N Nguyen · 2022
Cited alongside, same era.
Codegen: An open large language model for code with multi-turn program synthesis
Original
Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong · 2022
Cited alongside, same era.
Learning to construct better mutation faults
Zhao Tian, Junjie Chen, Qihao Zhu, Junjie Yang, and Lingming Zhang · 2022
Cited alongside, same era.
Recommending root-cause and mitigation steps for cloud incidents using large language models
Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, and Saravan Rajmohan · 2023
Cited alongside, same era.
Impact of code language models on automated program repair
Nan Jiang, Kevin Liu, Thibaud Lutellier, and Lin Tan · 2023
Cited alongside, same era.
Swe-bench: Can language models resolve real-world github issues?
Original
Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan · 2023
Cited alongside, same era.
Cct5: A code-change-oriented pre-trained model
Bo Lin, Shangwen Wang, Zhongxin Liu, Yepang Liu, Xin Xia, and Xiaoguang Mao · 2023
Cited alongside, same era.
Prompt text classifications with transformer models! an exemplary introduction to prompt-based learning with large language models
Christian WF Mayer, Sabrina Ludwig, and Steffen Brandt · 2023
Cited alongside, same era.
Smt solver validation empowered by large pre-trained language models
Maolin Sun, Yibiao Yang, Yang Wang, Ming Wen, Haoxiang Jia, and Yuming Zhou · 2023
Cited alongside, same era.
How practitioners expect code completion?
Chaozheng Wang, Junhao Hu, Cuiyun Gao, Yu Jin, Tao Xie, Hailiang Huang, Zhenyu Lei, and Yuetang Deng · 2023
Cited alongside, same era.
Document-level machine translation with large language models
Original
Longyue Wang, Chenyang Lyu, Tianbo Ji, Zhirui Zhang, Dian Yu, Shuming Shi, and Zhaopeng Tu · 2023
Cited alongside, same era.
Natural language to code: How far are we?
Shangwen Wang, Mingyang Geng, Bo Lin, Zhensu Sun, Ming Wen, Yepang Liu, Li Li, Tegawendé F Bissyandé, and Xiaoguang Mao · 2023
Cited alongside, same era.

Then

Benchmarking large language models for news summarization
Original
Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, Kathleen McKeown, and Tatsunori B Hashimoto · 2023
Later among the works it cites.
Coder: Issue resolving with multi-agent and task graphs, 2024
Dong Chen, Shaoxin Lin, Muhan Zeng, Daoguang Zan, Jian-Gang Wang, Anton Cheshkov, Jun Sun, Hao Yu, Guoliang Dong, Artem Aliev, Jie Wang, Xiao Cheng, Guangtai Liang, Yuchi Ma, Pan Bian, Tao Xie, and Qianxiang Wang · 2024
Closest in time.
Automatic root cause analysis via large language models for cloud incidents
Yinfang Chen, Huaibing Xie, Minghua Ma, Yu Kang, Xin Gao, Liu Shi, Yunjie Cao, Xuedong Gao, Hao Fan, Ming Wen, et al · 2024
Closest in time.
Generalization-enhanced code vulnerability detection via multi-task instruction fine-tuning
Original
Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, and Hai Jin · 2024
Closest in time.
Large language models are few-shot summarizers: Multi-intent comment generation via in-context learning
Mingyang Geng, Shangwen Wang, Dezun Dong, Haotian Wang, Ge Li, Zhi Jin, Xiaoguang Mao, and Xiangke Liao · 2024
Closest in time.
One size does not fit all: Multi-granularity patch generation for better automated program repair
Bo Lin, Shangwen Wang, Ming Wen, Liqian Chen, and Xiaoguang Mao · 2024
Closest in time.
Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation
Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang · 2024
Closest in time.
Starcoder 2 and the stack v2: The next generation
Original
Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al · 2024
Closest in time.
Agentfl: Scaling llm-based fault localization to project-level context
Original
Yihao Qin, Shangwen Wang, Yiling Lou, Jinhao Dong, Kaixin Wang, Xiaoling Li, and Xiaoguang Mao · 2024
Closest in time.
Opendevin: An open platform for ai software developers as generalist agents
Original
Xingyao Wang, Boxuan Li, Yufan Song, Frank F Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, et al · 2024
Closest in time.
Agentless: Demystifying llm-based software engineering agents
Original
Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, and Lingming Zhang · 2024
Closest in time.
Swe-agent: Agent-computer interfaces enable automated software engineering
Original
John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press · 2024
Closest in time.
Exploring and unleashing the power of large language models in automated code translation
Zhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung, Jia Li, Shuo Liu, Yifan Hong, Xiaoxue Ma, Zhi Jin, and Ge Li · 2024
Closest in time.
Maltracker: A fine-grained npm malware tracker copiloted by llm-enhanced dataset
Zeliang Yu, Ming Wen, Xiaochen Guo, and Hai Jin · 2024
Closest in time.
Autocoderover: Autonomous program improvement
Original
Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury · 2024
Closest in time.
Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence
Original
Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y Wu, Yukun Li, Huazuo Gao, Shirong Ma, et al · 2024
Closest in time.
Sketch then generate: Providing incremental user feedback and guiding llm code generation through language-oriented code sketches
Original
Chen Zhu-Tian, Zeyu Xiong, Xiaoshuo Yao, and Elena Glassman · 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…