[论文解读] How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering

Christoph Treude, Marco Aurélio Gerosa|ArXiv.org|Jan 15, 2025

Ethics and Social Impacts of AI被引用 3

一句话总结

论文提出了软件工程中11种开发者-人工智能交互类型的分类，并概述了一个研究议程，以改善AI辅助开发、信任和可用性。

ABSTRACT

Artificial intelligence (AI), including large language models and generative AI, is emerging as a significant force in software development, offering developers powerful tools that span the entire development lifecycle. Although software engineering research has extensively studied AI tools in software development, the specific types of interactions between developers and these AI-powered tools have only recently begun to receive attention. Understanding and improving these interactions has the potential to enhance productivity, trust, and efficiency in AI-driven workflows. In this paper, we propose a taxonomy of interaction types between developers and AI tools, identifying eleven distinct interaction types, such as auto-complete code suggestions, command-driven actions, and conversational assistance. Building on this taxonomy, we outline a research agenda focused on optimizing AI interactions, improving developer control, and addressing trust and usability challenges in AI-assisted development. By establishing a structured foundation for studying developer-AI interactions, this paper aims to stimulate research on creating more effective, adaptive AI tools for software development.

研究动机与目标

• 研究AI工具在软件开发生命周期中的使用动机。
• 引入开发者-AI交互类型的结构化分类。
• 强调对生产力、信任和AI驱动工作流采用的影响。
• 提供优化交互并解决可用性和隐私问题的研究议程。

提出的方法

• 将现有AI辅助开发工具和交互模态综合成一个统一的分类学。
• 用触发器、AI响应、开发者输出和示例来描述11种交互类型。
• 以Copilot、ChatGPT、Sourcegraph Cody和GitLab Auto DevOps等真实工具为基础来支撑分类学。

实验结果

研究问题

• RQ1 在软件工程中，开发者与AI工具之间最常见的交互类型有哪些？
• RQ2 不同的交互类型如何影响生产力、代码质量和用户满意度？
• RQ3 哪些设计因素会影响对AI驱动开发工具的信任、采用和正确使用？
• RQ4 在AI辅助工作流中，如何在上下文感知、开发者控制和隐私之间取得平衡？
• RQ5 哪些机制可以缓解AI幻觉并确保安全地集成到工作流中？

主要发现

• 识别出十一种不同的交互类型，范围从自动完成和命令驱动的动作到对话式帮助和事件触发。
• 讨论触发器、AI响应、开发者输出和具体示例如何塑造每种交互类型。
• 面向未来的研究议程，涵盖有效性、信任、上下文感知、定制化、认知负担、伦理和隐私。