一句话：通过实证对比人-人与人-AI结对编程的知识转移，发现频次与主题相似，但对AI建议审查更少且其能提醒代码细节。
知识转移是人类协作的基础，在软件工程中十分常见，结对编程便是典型场景。随着AI编码助手的兴起，开发者不仅与人类伙伴协作，也开始与AI结对编程。尽管已有研究证实人类结对编程中存在知识转移，但与AI编码助手之间的知识转移效果仍不明确。为分析人-人与人-AI两种设置下的知识转移，本文开展了一项实证研究：一组开发者结对且无AI支持完成任务，另一组独立开发者使用GitHub Copilot完成同一任务。作者扩展了已有的知识转移框架，并采用半自动评估流程，比较两种设置下知识转移事件的数量与内容差异。研究发现，两种设置中成功知识转移事件的频率相似，且主题类别存在重叠。两个关键发现是：开发者对GitHub Copilot建议的审查程度低于对人类结对伙伴的审查，但Copilot也能微妙地提醒开发者注意其可能忽略的重要代码细节。
Knowledge transfer is fundamental to human collaboration and is therefore common in software engineering. Pair programming is a prominent instance. With the rise of AI coding assistants, developers now not only work with human partners but also, as some claim, with AI pair programmers. Although studies confirm knowledge transfer during human pair programming, its effectiveness with AI coding assistants remains uncertain.To analyze knowledge transfer in both human–human and human–AI settings, we conducted an empirical study where developer pairs solved a programming task without AI support, while a separate group of individual developers completed the same task using the AI coding assistant GitHub Copilot. We extended an existing knowledge transfer framework and employed a semi-automated evaluation pipeline to assess differences in knowledge transfer episodes across both settings. We found a similar frequency of successful knowledge transfer episodes and overlapping topical categories across both settings. Two of our key findings are that developers tend to accept GitHub Copilot’s suggestions with less scrutiny than those from human pair programming partners, but also that GitHub Copilot can subtly remind developers of important code details they might otherwise overlook.
DOI 原文 ·
@inproceedings{paperbot9342,
title = {An Empirical Study of Knowledge Transfer in AI Pair Programming},
author = {Alisa Welter and Niklas Schneider and Tobias Dick and Kallistos Weis and Christof Tinnes and Marvin Wyrich and Sven Apel},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00022}
}