nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo journalinfonormal searchdiv searchzone qikanlogo popupnotification paper paperNew
2026, 03, No.375 119-129
OSSerCopilot: An LLM-driven Tutoring System for Fostering Open Source Competency in Software Engineering Education
基金项目(Foundation): supported by the National Natural Science Foundation of China (62202022, 92582204, and 62572030); the Fundamental Research Funds for the Central Universities; the exploratory elective projects of the State Key Laboratory of Complex and Critical Software Environments
邮箱(Email): fangliu@buaa.edu.cn;
DOI: 10.16512/j.cnki.jsjjy.2026.03.039
投稿时间: 2025-10-13
投稿日期(年): 2025
终审时间: 2025-11-13
终审日期(年): 2025
审稿周期(年): 1
发布时间: 2026-03-09
出版时间: 2026-03-09
移动端阅读
摘要:

In the context of large language model (LLM) reshaping software engineering education,this paper presents OSSerCopilot,a LLM-based tutoring system designed to address the critical challenge faced by newcomers (especially student contributors) in open source software (OSS) communities.Leveraging natural language processing,code semantic understanding,and learner profiling,the system functions as an intelligent tutor to scaffold three core competency domains:contribution guideline interpretation,project architecture comprehension,and personalized task matching.By transforming traditional onboarding barriers—such as complex contribution documentation and opaque project structures—into interactive learning journeys,OSSerCopilot enables newcomers to complete their first OSS contribution more easily and confidently.This paper highlights how LLM technologies can redefine software engineering education by bridging the gap between theoretical knowledge and practical OSS participation,offering implications for curriculum design,competency assessment,and sustainable OSS ecosystem cultivation.A demonstration video of the system is available at https://figshare.com/articles/media/OSSerCopilot_Introduction_mp4/29510276.

关键词:
Abstract:

In the context of large language model (LLM) reshaping software engineering education,this paper presents OSSerCopilot,a LLM-based tutoring system designed to address the critical challenge faced by newcomers (especially student contributors) in open source software (OSS) communities.Leveraging natural language processing,code semantic understanding,and learner profiling,the system functions as an intelligent tutor to scaffold three core competency domains:contribution guideline interpretation,project architecture comprehension,and personalized task matching.By transforming traditional onboarding barriers—such as complex contribution documentation and opaque project structures—into interactive learning journeys,OSSerCopilot enables newcomers to complete their first OSS contribution more easily and confidently.This paper highlights how LLM technologies can redefine software engineering education by bridging the gap between theoretical knowledge and practical OSS participation,offering implications for curriculum design,competency assessment,and sustainable OSS ecosystem cultivation.A demonstration video of the system is available at https://figshare.com/articles/media/OSSerCopilot_Introduction_mp4/29510276.

参考文献

[1]Levine S S,Prietula M J.Open collaboration for innovation:Principles and performance[J].Organization Science,2014,25(5):1414-1433.

[2]Scacchi W.Free/open source software development:Recent research results and emerging opportunities[C]//Proceedings of the 6th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering:Companion Papers.New York:ACM,2007:459-468.

[3]Andersen-Gott M,Ghinea G,Bygstad B.Why do commercial companies contribute to open source software?[J].International Journal of Information Management,2012,32(2):106-117.

[4]The National People’s Congress of the People’s Republic of China.Outline of the 14th five-year plan for national economic and social development of the People’s Republic of China and the long-range objectives through 2035[EB/OL].(2021-03-13)[2025-10-09].https://www.gov.cn/xinwen/2021-03/13/content_5592681.htm.

[5]Steinmacher I,Silva M A G,Gerosa M A.Barriers faced by newcomers to open source projects:a systematic review[C]//Proceedings of the 10th IFIP WG 2.13 International Conference on Open Source Systems on Open Source Software:Mobile Open Source Technologies.San José:Springer,2014:153-163.

[6]Tan X,Long X,Zhu Y H,et al.Revolutionizing newcomers’ onboarding process in OSS communities:the future AI mentor[J].Proceedings of the ACM on Software Engineering,2025,2(FSE):FSE050.

[7]Tan X,Zhou M H,Zhang L.Understanding mentors’ engagement in OSS communities via Google summer of code[J].IEEE Transactions on Software Engineering,2023,49(5):3106-3130.

[8]Mendez C,Padala H S,Steine-Hanson Z,et al.Open source barriers to entry,revisited:a sociotechnical perspective[C]//Proceedings of the 40th International Conference on Software Engineering.New York:IEEE,2018:1004-1015.

[9]Elazhary O,Storey M A,Ernst N,et al.Do as I do,not as I say:Do contribution guidelines match the GitHub contribution process?[C]//Proceedings of the 2019 IEEE International Conference on Software Maintenance and Evolution (ICSME).New York:IEEE,2019:286-290.

[10]Godfrey,Tu Q.Evolution in open source software:A case study[C]//Proceedings of the 2000 International Conference on Software Maintenance.New York:IEEE,2000:131-142.

[11]Tan X,Zhou M H,Sun Z Y.A first look at good first issues on GitHub[C]//Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering.New York:ACM,2020:398-409.

[12]Tan X,Chen Y R,Wu H H,et al.Is it enough to recommend tasks to newcomers?Understanding mentoring on good first issues[C]//Proceedings of the IEEE/ACM 45th International Conference on Software Engineering (ICSE).New York:IEEE,2023:653-664.

[13]Nam D,Macvean A,Hellendoorn V,et al.Using an LLM to help with code understanding[C]//Proceedings of the IEEE/ACM 46th International Conference on Software Engineering.New York:IEEE,2024:1184-1196.

[14]Granić A,Marangunić N.Technology acceptance model in educational context:a systematic literature review[J].British Journal of Educational Technology,2019,50(5):2572-2593.

基本信息:

DOI:10.16512/j.cnki.jsjjy.2026.03.039

中图分类号:G642;TP311.5-4;TP18

引用信息:

[1]Xin Tan,Jingyi Tan,Weimiao Ren,等.OSSerCopilot: An LLM-driven Tutoring System for Fostering Open Source Competency in Software Engineering Education[J].计算机教育,2026,No.375(03):119-129.DOI:10.16512/j.cnki.jsjjy.2026.03.039.

基金信息:

supported by the National Natural Science Foundation of China (62202022, 92582204, and 62572030); the Fundamental Research Funds for the Central Universities; the exploratory elective projects of the State Key Laboratory of Complex and Critical Software Environments

投稿时间:

2025-10-13

投稿日期(年):

2025

终审时间:

2025-11-13

终审日期(年):

2025

审稿周期(年):

1

发布时间:

2026-03-09

出版时间:

2026-03-09

引用

GB/T 7714-2015 格式引文
MLA格式引文
APA格式引文