[论文解读] Generative Artificial Intelligence for Software Engineering -- A Research Agenda

Anh Nguyen‐Duc, Beatriz Cabrero‐Daniel+13 more|arXiv (Cornell University)|Oct 28, 2023

Software Engineering Research被引用 12

一句话总结

本文提出了软件工程中生成式人工智能（GenAI）的研究议程，识别出跨11个软件工程领域的78个开放研究问题，来自文献综述和焦点小组，并概述挑战与未来方向。

ABSTRACT

Generative Artificial Intelligence (GenAI) tools have become increasingly prevalent in software development, offering assistance to various managerial and technical project activities. Notable examples of these tools include OpenAIs ChatGPT, GitHub Copilot, and Amazon CodeWhisperer. Although many recent publications have explored and evaluated the application of GenAI, a comprehensive understanding of the current development, applications, limitations, and open challenges remains unclear to many. Particularly, we do not have an overall picture of the current state of GenAI technology in practical software engineering usage scenarios. We conducted a literature review and focus groups for a duration of five months to develop a research agenda on GenAI for Software Engineering. We identified 78 open Research Questions (RQs) in 11 areas of Software Engineering. Our results show that it is possible to explore the adoption of GenAI in partial automation and support decision-making in all software development activities. While the current literature is skewed toward software implementation, quality assurance and software maintenance, other areas, such as requirements engineering, software design, and software engineering education, would need further research attention. Common considerations when implementing GenAI include industry-level assessment, dependability and accuracy, data accessibility, transparency, and sustainability aspects associated with the technology. GenAI is bringing significant changes to the field of software engineering. Nevertheless, the state of research on the topic still remains immature. We believe that this research agenda holds significance and practical value for informing both researchers and practitioners about current applications and guiding future research.

研究动机与目标

• 绘制软件工程中GenAI的现状并识别知识空白。
• 将开放的研究问题整理成跨越软件工程活动的连贯轨道。
• 为研究人员和从业者提供关于GenAI如何支持软件工程任务的实用指南。
• 突出挑战（如可靠性、数据获取、伦理、透明度）和未来机会。

提出的方法

• 进行了聚焦的文献综述，利用Google Scholar、Scopus、arXiv和PaperwithCode，并进行前向/后向溯源。
• 在2023年4月到9月举办了四次结构化焦点小组，邀请软件工程研究人员头脑风暴并验证研究问题。
• 将焦点小组和文献综述的发现综合成一个11轨道的研究议程。
• 把来自两个国际活动/工作坊（AI辅助敏捷软件开发与RESET）的洞见融入，以使议程更具 grounding。
• 报告焦点小组方法的有效性威胁及其缓解措施。

Figure 1: Several optimal parameter fine-tuning methods [ 34 ]

实验结果

研究问题

• RQ1 GenAI 如何支持需求获取？
• RQ2 GenAI 如何从高层用户输入有效生成需求规格？
• RQ3 GenAI 如何促进将需求与领域约束和法规进行自动验证？
• RQ4 GenAI 如何用于预测变更请求？
• RQ5 在预获取、获取、规格、分析和验证阶段采用GenAI进行需求工程任务时，面临哪些挑战和威胁？

主要发现

• 在11个软件工程领域中识别出78个开放研究问题。
• GenAI 的应用可以在部分自动化并支持所有软件工程活动中的决策。
• 现有文献偏向软件实现、质量保证和维护；需求工程、设计和软件工程教育等其他领域需要更多研究。
• 软件工程中GenAI的常见考量包括可依赖性、准确性、数据可获取性、透明度和可持续性。
• 该研究议程旨在为研究者和从业者在利用GenAI的同时，解决开放挑战和未来方向提供指导。
• GenAI正在给软件工程带来显著变革，但该领域的研究成熟度仍然不足。

Figure 2: Research Agenda on GenAI for Software Engineering