arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01156cs.SE
收藏

基于传统与大语言模型支持的低代码编程实证研究

An Empirical Study on Low-Code Programming using Traditional vs Large Language Model Support

School of Software Engineering, Sun Yat-sen University(中山大学软件学院);The University of Melbourne(墨尔本大学);The University of Western Australia(西澳大学);Faculty of Information Technology, Monash University(蒙纳士大学信息技术学院);School of Artificial Intelligence, Sun Yat-sen University(中山大学人工智能学院);Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China(电子科技大学深圳高等研究院);University of Glasgow(格拉斯哥大学);Zhuhai Key Laboratory of Trusted Large Language Models(珠海可信大模型重点实验室)

Yongkun Liu, Jiachi Chen, Tingting Bi, John Grundy, Yanlin Wang, Jianxing Yu, Ting Chen, Yutian Tang, Zibin Zheng

AI总结:

本研究通过实证分析比较了传统与基于大语言模型的低代码编程方法在应用中的差异及影响。

摘要:

低代码编程(LCP)指的是通过更高层次的抽象模型进行编程,从而减少手动工作,提高编程效率,并降低业余开发者的学习成本。许多LCP工具已经迅速发展,并受益于可视化编程语言(VPLs)和演示式编程(PBD)的概念。随着在软件工程中使用大语言模型(LLMs)的兴趣大幅增加,基于LLMs的LCP开始变得越来越重要。然而,传统方法和基于LLMs的LCP在技术原理和应用场景上有显著差异。理解这两种方法在LCP应用中用户的关键差异和特征对于LCP提供商改进现有和开发新LCP工具以及更好地帮助用户选择合适的LCP技术至关重要。我们对传统LCP和基于LLMs的LCP进行了实证研究。我们分析了过去三年Stack Overflow(SO)上开发者讨论,并探讨了传统LCP和基于LLMs的LCP特征及开发者反馈的相似性和差异性。我们的发现表明,尽管传统LCP和基于LLMs的LCP在主要使用场景上有共同点,但它们在范围、限制和软件开发生命周期中的使用上有显著差异,尤其是在实施阶段。我们还探讨了LLMs如何影响和整合到LCP中,讨论了基于LLMs的LCP的最新技术发展,例如其与VPLs的整合以及LLM代理在软件工程中的应用。

英文摘要:

Low-code programming (LCP) refers to programming using models at higher levels of abstraction, resulting in less manual and more efficient programming, and reduced learning effort for amateur developers. Many LCP tools have rapidly evolved and have benefited from the concepts of visual programming languages (VPLs) and programming by demonstration (PBD). With the huge increase in interest in using large language models (LLMs) in software engineering, LLM-based LCP has begun to become increasingly important. However, the technical principles and application scenarios of traditional approaches to LCP and LLM-based LCP are significantly different. Understanding these key differences and characteristics in the application of the two approaches to LCP by users is crucial for LCP providers in improving existing and developing new LCP tools and in better assisting users in choosing the appropriate LCP technology. We conducted an empirical study of both traditional LCP and LLM-based LCP. We analyzed developers' discussions on Stack Overflow (SO) over the past three years and then explored the similarities and differences between traditional LCP and LLM-based LCP features and developer feedback. Our findings reveal that while traditional LCP and LLM-based LCP share common primary usage scenarios, they significantly differ in scope, limitations, and usage throughout the software development lifecycle, particularly during the implementation phase. We also examine how LLMs impact and integrate with LCP, discussing the latest technological developments in LLM-based LCP, such as its integration with VPLs and the application of LLM Agents in software engineering.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑