---
title: "CodeR: Issue Resolving with Multi-Agent and Task Graphs (2024)"
description: "The paper tackles automatic resolution of GitHub issues, measured with SWE-bench and its cleaner… 43 references, cited by 13 papers here."
authors: ["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", "Qianxiang Wang"]
year: 2024
venue: "arXiv:2406.01304"
source: "https://arxiv.org/abs/2406.01304"
doi: "10.48550/arxiv.2406.01304"
arxiv: "2406.01304"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chen-2024-coder-issue-resolving-multi-agent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2024-coder-issue-resolving-multi-agent/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/9/) / CodeR: Issue Resolving with Multi-Agent and Task Graphs

# CodeR: Issue Resolving with Multi-Agent and Task Graphs

**Authors:** [Dong Chen](https://md.research.elamur.ai/free/en/authors/dong-chen/), Shaoxin Lin, Muhan Zeng, [Daoguang Zan](https://md.research.elamur.ai/free/en/authors/daoguang-zan/), Jian-Gang Wang, Anton Cheshkov, [Jun Sun](https://md.research.elamur.ai/free/en/authors/jun-sun/), [Hao Yu](https://md.research.elamur.ai/free/en/authors/hao-yu/), Guoliang Dong, Artem Aliev, Jie Wang, [Xiao Cheng](https://md.research.elamur.ai/free/en/authors/xiao-cheng/), Guangtai Liang, Yuchi Ma, Pan Bian, Tao Xie and Qianxiang Wang · **Year:** 2024 · **Venue:** arXiv:2406.01304 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2406.01304) · [PDF](https://arxiv.org/pdf/2406.01304) · [DOI 10.48550/arxiv.2406.01304](https://doi.org/10.48550/arxiv.2406.01304) · [arXiv 2406.01304](https://arxiv.org/abs/2406.01304)

**Citations:** 13 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper tackles automatic resolution of GitHub issues, measured with SWE-bench and its cleaner subset SWE-bench lite. Earlier systems such as SWE-agent and AutoCodeRover use a single LLM agent that picks each next step as it goes. CodeR instead splits the work among five specialised agents: Manager, Reproducer, Fault Localizer, Editor and Verifier. Each agent can use only a limited set of actions, which makes each decision simpler. Plans are written ahead of time as task graphs in JSON. The system parses these graphs and executes them exactly, so it does not depend on the LLM following a long text plan or remembering it. CodeR reuses actions from SWE-agent and AutoCodeRover and adds new ones: plan selection, retrieval of similar past issues, test running, reporting, and fault localization. The fault localization step combines code coverage from LLM-generated reproduction tests and repository tests with BM25. With a single submission per issue, CodeR resolves 28.33% of SWE-bench lite, a new state of the art at the time. The work suggests that human-designed plans and classic software-engineering techniques make LLM agents more reliable.

## Key points
- CodeR solves 85 of 300 SWE-bench lite issues (28.33%) with one submission per issue. SWE-bench itself contains 2,294 real issues drawn from 12 Python libraries.
- There are five agent roles and 23 actions (0–22). Actions 1–10 come from SWE-agent, and actions 11–17 are improved versions of AutoCodeRover search. Only the Manager may plan and submit.
- Task graphs are JSON plans that specify an entry agent, the tasks for each role, and where to hand off on success or failure. New strategies can be added without changing code.
- In an ablation on 11 resolved issues out of 50 (22%), the result fell to 10% without the multi-agent design and task graphs. It fell to 14% without fault localization, which also raised cost from $3.09 to $3.19 per issue.
- The code is published at github.com/NL2Code/CodeR.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works

## Cite

Cite as: 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. CodeR: Issue Resolving with Multi-Agent and Task Graphs. arXiv:2406.01304.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{chen2024coder,
  title = {{CodeR: Issue Resolving with Multi-Agent and Task Graphs}},
  author = {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},
  year = {2024},
  doi = {10.48550/arxiv.2406.01304},
  eprint = {2406.01304},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2406.01304}
}
```

- [← previous CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models](https://md.research.elamur.ai/free/en/papers/liu-2024-cmm-math-chinese-multimodal-math/)
- [next → DevBench: A multimodal developmental benchmark for language learning](https://md.research.elamur.ai/free/en/papers/tan-2024-devbench-multimodal-developmental-benchmark-language/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/9/)

## References

43 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. [Swe-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) arXiv preprint arXiv:2310.06770, 2023.
2. Daoguang Zan, Bei Chen, Fengji Zhang, Dianjie Lu, Bingchao Wu, Bei Guan, Wang Yongji, and Jian-Guang Lou. Large language models meet nl2code: A survey. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7443–7464, 2023. [find](https://scholar.google.com/scholar?q=Daoguang+Zan%2C+Bei+Chen%2C+Fengji+Zhang%2C+Dianjie+Lu%2C+Bingchao+Wu%2C+Bei+Guan%2C+Wang+Yongji%2C+and+Jian%2DGuang+Lou%2E+Large+language+models+meet+nl2code%3A+A+survey%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the)
3. Ziyin Zhang, Chaoyu Chen, Bingchang Liu, Cong Liao, Zi Gong, Hang Yu, Jianguo Li, and Rui Wang. A survey on language models for code. arXiv preprint arXiv:2311.07989, 2023. — [arXiv:2311.07989](https://arxiv.org/abs/2311.07989) [find](https://scholar.google.com/scholar?q=Ziyin+Zhang%2C+Chaoyu+Chen%2C+Bingchang+Liu%2C+Cong+Liao%2C+Zi+Gong%2C+Hang+Yu%2C+Jianguo+Li%2C+and+Rui+Wang%2E+A+survey+on+language+models+for+code%2E+arXiv+preprint+arXiv%3A2311%2E07989%2C+2023%2E+%E2%80%94+%5BarXiv%3A2311%2E07989%5D%28https%3A)
4. Zibin Zheng, Kaiwen Ning, Yanlin Wang, Jingwen Zhang, Dewu Zheng, Mingxi Ye, and Jiachi Chen. A survey of large language models for code: Evolution, benchmarking, and future trends. arXiv preprint arXiv:2311.10372, 2023. — [arXiv:2311.10372](https://arxiv.org/abs/2311.10372) [find](https://scholar.google.com/scholar?q=Zibin+Zheng%2C+Kaiwen+Ning%2C+Yanlin+Wang%2C+Jingwen+Zhang%2C+Dewu+Zheng%2C+Mingxi+Ye%2C+and+Jiachi+Chen%2E+A+survey+of+large+language+models+for+code%3A+Evolution%2C+benchmarking%2C+and+future+trends%2E+arXiv+preprint+arX)
5. OpenAI. Hello gpt-4o. 2024. [https://openai.com/index/hello-gpt-4o](https://openai.com/index/hello-gpt-4o). [↗](https://openai.com/index/hello-gpt-4o)
6. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774, 2023.
7. Yuntong Zhang, Haifeng Ruan, Zhiyu Fan, and Abhik Roychoudhury. Autocoderover: Autonomous program improvement. arXiv preprint arXiv:2404.05427, 2024. — [arXiv:2404.05427](https://arxiv.org/abs/2404.05427) [find](https://scholar.google.com/scholar?q=Yuntong+Zhang%2C+Haifeng+Ruan%2C+Zhiyu+Fan%2C+and+Abhik+Roychoudhury%2E+Autocoderover%3A+Autonomous+program+improvement%2E+arXiv+preprint+arXiv%3A2404%2E05427%2C+2024%2E+%E2%80%94+%5BarXiv%3A2404%2E05427%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2404%2E05)
8. John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. [SWE-agent: Agent-computer interfaces enable automated software engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/). arXiv preprint arXiv:2405.15793, 2024.
9. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for multi-agent collaborative framework. In The Twelfth International Conference on Learning Representations, 2023. [find](https://scholar.google.com/scholar?q=Sirui+Hong%2C+Mingchen+Zhuge%2C+Jonathan+Chen%2C+Xiawu+Zheng%2C+Yuheng+Cheng%2C+Jinlin+Wang%2C+Ceyao+Zhang%2C+Zili+Wang%2C+Steven+Ka+Shing+Yau%2C+Zijuan+Lin%2C+et+al%2E+Metagpt%3A+Meta+programming+for+multi%2Dagent+collaborati)
10. Ying Wen, Yaodong Yang, Rui Luo, and Jun Wang. Modelling bounded rationality in multi-agent interactions by generalized recursive reasoning. arXiv preprint arXiv:1901.09216, 2019. — [arXiv:1901.09216](https://arxiv.org/abs/1901.09216) [find](https://scholar.google.com/scholar?q=Ying+Wen%2C+Yaodong+Yang%2C+Rui+Luo%2C+and+Jun+Wang%2E+Modelling+bounded+rationality+in+multi%2Dagent+interactions+by+generalized+recursive+reasoning%2E+arXiv+preprint+arXiv%3A1901%2E09216%2C+2019%2E+%E2%80%94+%5BarXiv%3A1901%2E09216%5D)
11. Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, and Jie Zhou. Improving multi-turn dialogue modelling with utterance rewriter. arXiv preprint arXiv:1906.07004, 2019. [find](https://scholar.google.com/scholar?q=Hui+Su%2C+Xiaoyu+Shen%2C+Rongzhi+Zhang%2C+Fei+Sun%2C+Pengwei+Hu%2C+Cheng+Niu%2C+and+Jie+Zhou%2E+Improving+multi%2Dturn+dialogue+modelling+with+utterance+rewriter%2E+arXiv+preprint+arXiv%3A1906%2E07004%2C+2019%2E)
12. paul gauthier. Aider, ai pair programming in your terminal. [https://aider.chat](https://aider.chat), 2024. [↗](https://aider.chat)
13. Eric Zelikman, Qian Huang, Gabriel Poesia, Noah Goodman, and Nick Haber. Parsel: Algorithmic reasoning with language models by composing decompositions. Advances in Neural Information Processing Systems, 36:31466–31523, 2023. [find](https://scholar.google.com/scholar?q=Eric+Zelikman%2C+Qian+Huang%2C+Gabriel+Poesia%2C+Noah+Goodman%2C+and+Nick+Haber%2E+Parsel%3A+Algorithmic+reasoning+with+language+models+by+composing+decompositions%2E+Advances+in+Neural+Information+Processing+Syste)
14. Daoguang Zan, Ailun Yu, Wei Liu, Dong Chen, Bo Shen, Wei Li, Yafen Yao, Yongshun Gong, Xiaolin Chen, Bei Guan, et al. [Codes: Natural language to code repository via multi-layer sketch](https://md.research.elamur.ai/free/en/papers/zan-2024-codes-natural-language-code-repository/). arXiv preprint arXiv:2403.16443, 2024.
15. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). arXiv preprint arXiv:2210.03629, 2022.
16. W Eric Wong, Ruizhi Gao, Yihao Li, Rui Abreu, and Franz Wotawa. A survey on software fault localization. IEEE Transactions on Software Engineering, 42(8):707–740, 2016. [find](https://scholar.google.com/scholar?q=W+Eric+Wong%2C+Ruizhi+Gao%2C+Yihao+Li%2C+Rui+Abreu%2C+and+Franz+Wotawa%2E+A+survey+on+software+fault+localization%2E+IEEE+Transactions+on+Software+Engineering%2C+42%288%29%3A707%E2%80%93740%2C+2016%2E)
17. Rui Abreu, Peter Zoeteweij, and Arjan JC Van Gemund. On the accuracy of spectrum-based fault localization. In Testing: Academic and industrial conference practice and research techniques-MUTATION (TAICPART-MUTATION 2007), pages 89–98. IEEE, 2007. [find](https://scholar.google.com/scholar?q=Rui+Abreu%2C+Peter+Zoeteweij%2C+and+Arjan+JC+Van+Gemund%2E+On+the+accuracy+of+spectrum%2Dbased+fault+localization%2E+In+Testing%3A+Academic+and+industrial+conference+practice+and+research+techniques%2DMUTATION+%28TAI)
18. James A Jones, Mary Jean Harrold, and John Stasko. Visualization of test information to assist fault localization. In Proceedings of the 24th international conference on Software engineering, pages 467–477, 2002. [find](https://scholar.google.com/scholar?q=James+A+Jones%2C+Mary+Jean+Harrold%2C+and+John+Stasko%2E+Visualization+of+test+information+to+assist+fault+localization%2E+In+Proceedings+of+the+24th+international+conference+on+Software+engineering%2C+pages+46)
19. Daming Zou, Jingjing Liang, Yingfei Xiong, Michael D Ernst, and Lu Zhang. An empirical study of fault localization families and their combinations. IEEE Transactions on Software Engineering, 47(2):332–347, 2019. [find](https://scholar.google.com/scholar?q=Daming+Zou%2C+Jingjing+Liang%2C+Yingfei+Xiong%2C+Michael+D+Ernst%2C+and+Lu+Zhang%2E+An+empirical+study+of+fault+localization+families+and+their+combinations%2E+IEEE+Transactions+on+Software+Engineering%2C+47%282%29%3A332)
20. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971, 2023.
21. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288, 2023.
22. Wei Tao, Yucheng Zhou, Wenqiang Zhang, and Yu Cheng. Magis: Llm-based multi-agent framework for github issue resolution. arXiv preprint arXiv:2403.17927, 2024. — [arXiv:2403.17927](https://arxiv.org/abs/2403.17927) [find](https://scholar.google.com/scholar?q=Wei+Tao%2C+Yucheng+Zhou%2C+Wenqiang+Zhang%2C+and+Yu+Cheng%2E+Magis%3A+Llm%2Dbased+multi%2Dagent+framework+for+github+issue+resolution%2E+arXiv+preprint+arXiv%3A2403%2E17927%2C+2024%2E+%E2%80%94+%5BarXiv%3A2403%2E17927%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
23. Claire Le Goues, ThanhVu Nguyen, Stephanie Forrest, and Westley Weimer. Genprog: A generic method for automatic software repair. Ieee transactions on software engineering, 38(1):54–72, 2011. [find](https://scholar.google.com/scholar?q=Claire+Le+Goues%2C+ThanhVu+Nguyen%2C+Stephanie+Forrest%2C+and+Westley+Weimer%2E+Genprog%3A+A+generic+method+for+automatic+software+repair%2E+Ieee+transactions+on+software+engineering%2C+38%281%29%3A54%E2%80%9372%2C+2011%2E)
24. Kui Liu, Anil Koyuncu, Dongsun Kim, and Tegawendé F Bissyandé. Tbar: Revisiting template-based automated program repair. In Proceedings of the 28th ACM SIGSOFT international symposium on software testing and analysis, pages 31–42, 2019. [find](https://scholar.google.com/scholar?q=Kui+Liu%2C+Anil+Koyuncu%2C+Dongsun+Kim%2C+and+Tegawend%C3%A9+F+Bissyand%C3%A9%2E+Tbar%3A+Revisiting+template%2Dbased+automated+program+repair%2E+In+Proceedings+of+the+28th+ACM+SIGSOFT+international+symposium+on+software+test)
25. Hoang Duong Thien Nguyen, Dawei Qi, Abhik Roychoudhury, and Satish Chandra. Semfix: Program repair via semantic analysis. In 2013 35th International Conference on Software Engineering (ICSE), pages 772–781. IEEE, 2013. [find](https://scholar.google.com/scholar?q=Hoang+Duong+Thien+Nguyen%2C+Dawei+Qi%2C+Abhik+Roychoudhury%2C+and+Satish+Chandra%2E+Semfix%3A+Program+repair+via+semantic+analysis%2E+In+2013+35th+International+Conference+on+Software+Engineering+%28ICSE%29%2C+pages+77)
26. Jiajun Jiang, Yingfei Xiong, Hongyu Zhang, Qing Gao, and Xiangqun Chen. Shaping program repair space with existing patches and similar code. In Proceedings of the 27th ACM SIGSOFT international symposium on software testing and analysis, pages 298–309, 2018. [find](https://scholar.google.com/scholar?q=Jiajun+Jiang%2C+Yingfei+Xiong%2C+Hongyu+Zhang%2C+Qing+Gao%2C+and+Xiangqun+Chen%2E+Shaping+program+repair+space+with+existing+patches+and+similar+code%2E+In+Proceedings+of+the+27th+ACM+SIGSOFT+international+sympos)
27. Anil Koyuncu, Kui Liu, Tegawendé F Bissyandé, Dongsun Kim, Jacques Klein, Martin Monperrus, and Yves Le Traon. Fixminer: Mining relevant fix patterns for automated program repair. Empirical Software Engineering, 25:1980–2024, 2020. [find](https://scholar.google.com/scholar?q=Anil+Koyuncu%2C+Kui+Liu%2C+Tegawend%C3%A9+F+Bissyand%C3%A9%2C+Dongsun+Kim%2C+Jacques+Klein%2C+Martin+Monperrus%2C+and+Yves+Le+Traon%2E+Fixminer%3A+Mining+relevant+fix+patterns+for+automated+program+repair%2E+Empirical+Software+E)
28. Qi Xin and Steven P Reiss. Leveraging syntax-related code for automated program repair. In 2017 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE), pages 660–670. IEEE, 2017. [find](https://scholar.google.com/scholar?q=Qi+Xin+and+Steven+P+Reiss%2E+Leveraging+syntax%2Drelated+code+for+automated+program+repair%2E+In+2017+32nd+IEEE%2FACM+International+Conference+on+Automated+Software+Engineering+%28ASE%29%2C+pages+660%E2%80%93670%2E+IEEE%2C+201)
29. Ming Wen, Junjie Chen, Rongxin Wu, Dan Hao, and Shing-Chi Cheung. Context-aware patch generation for better automated program repair. In Proceedings of the 40th international conference on software engineering, pages 1–11, 2018. [find](https://scholar.google.com/scholar?q=Ming+Wen%2C+Junjie+Chen%2C+Rongxin+Wu%2C+Dan+Hao%2C+and+Shing%2DChi+Cheung%2E+Context%2Daware+patch+generation+for+better+automated+program+repair%2E+In+Proceedings+of+the+40th+international+conference+on+software+en)
30. Jinru Hua, Mengshi Zhang, Kaiyuan Wang, and Sarfraz Khurshid. Sketchfix: a tool for automated program repair approach using lazy candidate generation. In Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineerin… [find](https://scholar.google.com/scholar?q=Jinru+Hua%2C+Mengshi+Zhang%2C+Kaiyuan+Wang%2C+and+Sarfraz+Khurshid%2E+Sketchfix%3A+a+tool+for+automated+program+repair+approach+using+lazy+candidate+generation%2E+In+Proceedings+of+the+2018+26th+ACM+Joint+Meeting)
31. Kui Liu, Anil Koyuncu, Dongsun Kim, and Tegawendé F Bissyandé. Avatar: Fixing semantic bugs with fix patterns of static analysis violations. In 2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER), pages 1–12. IEEE, 2019. [find](https://scholar.google.com/scholar?q=Kui+Liu%2C+Anil+Koyuncu%2C+Dongsun+Kim%2C+and+Tegawend%C3%A9+F+Bissyand%C3%A9%2E+Avatar%3A+Fixing+semantic+bugs+with+fix+patterns+of+static+analysis+violations%2E+In+2019+IEEE+26th+International+Conference+on+Software+Anal)
32. Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, and Denys Poshyvanyk. An empirical investigation into learning bug-fixing patches in the wild via neural machine translation. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineer… [find](https://scholar.google.com/scholar?q=Michele+Tufano%2C+Cody+Watson%2C+Gabriele+Bavota%2C+Massimiliano+Di+Penta%2C+Martin+White%2C+and+Denys+Poshyvanyk%2E+An+empirical+investigation+into+learning+bug%2Dfixing+patches+in+the+wild+via+neural+machine+tran)
33. Saikat Chakraborty, Miltiadis Allamanis, and Baishakhi Ray. Codit: Code editing with tree-based neural machine translation. arXiv preprint arXiv:1810.00314, 2018. [find](https://scholar.google.com/scholar?q=Saikat+Chakraborty%2C+Miltiadis+Allamanis%2C+and+Baishakhi+Ray%2E+Codit%3A+Code+editing+with+tree%2Dbased+neural+machine+translation%2E+arXiv+preprint+arXiv%3A1810%2E00314%2C+2018%2E)
34. Yi Li, Shaohua Wang, and Tien N Nguyen. Dlfix: Context-based code transformation learning for automated program repair. In Proceedings of the ACM/IEEE 42nd international conference on software engineering, pages 602–614, 2020. [find](https://scholar.google.com/scholar?q=Yi+Li%2C+Shaohua+Wang%2C+and+Tien+N+Nguyen%2E+Dlfix%3A+Context%2Dbased+code+transformation+learning+for+automated+program+repair%2E+In+Proceedings+of+the+ACM%2FIEEE+42nd+international+conference+on+software+enginee)
35. Thibaud Lutellier, Hung Viet Pham, Lawrence Pang, Yitong Li, Moshi Wei, and Lin Tan. Coconut: combining context-aware neural translation models using ensemble for program repair. In Proceedings of the 29th ACM SIGSOFT international symposium on software testing and analysis, pages 101–114, 2020. [find](https://scholar.google.com/scholar?q=Thibaud+Lutellier%2C+Hung+Viet+Pham%2C+Lawrence+Pang%2C+Yitong+Li%2C+Moshi+Wei%2C+and+Lin+Tan%2E+Coconut%3A+combining+context%2Daware+neural+translation+models+using+ensemble+for+program+repair%2E+In+Proceedings+of+the)
36. Nan Jiang, Thibaud Lutellier, and Lin Tan. Cure: Code-aware neural machine translation for automatic program repair. In 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), pages 1161–1173. IEEE, 2021. [find](https://scholar.google.com/scholar?q=Nan+Jiang%2C+Thibaud+Lutellier%2C+and+Lin+Tan%2E+Cure%3A+Code%2Daware+neural+machine+translation+for+automatic+program+repair%2E+In+2021+IEEE%2FACM+43rd+International+Conference+on+Software+Engineering+%28ICSE%29%2C+page)
37. Qihao Zhu, Zeyu Sun, Yuan-an Xiao, Wenjie Zhang, Kang Yuan, Yingfei Xiong, and Lu Zhang. A syntax-guided edit decoder for neural program repair. In Proceedings of the 29th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering, pages 34… [find](https://scholar.google.com/scholar?q=Qihao+Zhu%2C+Zeyu+Sun%2C+Yuan%2Dan+Xiao%2C+Wenjie+Zhang%2C+Kang+Yuan%2C+Yingfei+Xiong%2C+and+Lu+Zhang%2E+A+syntax%2Dguided+edit+decoder+for+neural+program+repair%2E+In+Proceedings+of+the+29th+ACM+joint+meeting+on+Europea)
38. He Ye, Matias Martinez, and Martin Monperrus. Neural program repair with execution-based backpropagation. In Proceedings of the 44th international conference on software engineering, pages 1506–1518, 2022. [find](https://scholar.google.com/scholar?q=He+Ye%2C+Matias+Martinez%2C+and+Martin+Monperrus%2E+Neural+program+repair+with+execution%2Dbased+backpropagation%2E+In+Proceedings+of+the+44th+international+conference+on+software+engineering%2C+pages+1506%E2%80%931518%2C+)
39. Qihao Zhu, Zeyu Sun, Wenjie Zhang, Yingfei Xiong, and Lu Zhang. Tare: Type-aware neural program repair. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), pages 1443–1455. IEEE, 2023. [find](https://scholar.google.com/scholar?q=Qihao+Zhu%2C+Zeyu+Sun%2C+Wenjie+Zhang%2C+Yingfei+Xiong%2C+and+Lu+Zhang%2E+Tare%3A+Type%2Daware+neural+program+repair%2E+In+2023+IEEE%2FACM+45th+International+Conference+on+Software+Engineering+%28ICSE%29%2C+pages+1443%E2%80%931455%2E+)
40. Hui Yang, Sifu Yue, and Yunzhong He. Auto-gpt for online decision making: Benchmarks and additional opinions. arXiv preprint arXiv:2306.02224, 2023. [find](https://scholar.google.com/scholar?q=Hui+Yang%2C+Sifu+Yue%2C+and+Yunzhong+He%2E+Auto%2Dgpt+for+online+decision+making%3A+Benchmarks+and+additional+opinions%2E+arXiv+preprint+arXiv%3A2306%2E02224%2C+2023%2E)
41. Assemble, configure, and deploy autonomous ai agents in your browser. GitHub, 2023. [https://github.com/](https://github.com/) reworkd/AgentGPT. [↗](https://github.com/)
42. The innovation engine for generative ai applications. Dify.AI, 2024. [https://dify.ai](https://dify.ai). [↗](https://dify.ai)
43. Empower ai with your expertise. labring, 2024. [https://fastgpt.run](https://fastgpt.run). [↗](https://fastgpt.run)

*Updated 1 November 2026*