From Developer Pairs to AI Copilots: A Comparative Study on Knowledge Transfer
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910989356630016 |
|---|---|
| author | Welter, Alisa Schneider, Niklas Dick, Tobias Weis, Kallistos Tinnes, Christof Wyrich, Marvin Apel, Sven |
| author_facet | Welter, Alisa Schneider, Niklas Dick, Tobias Weis, Kallistos Tinnes, Christof Wyrich, Marvin Apel, Sven |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04785 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Developer Pairs to AI Copilots: A Comparative Study on Knowledge Transfer Welter, Alisa Schneider, Niklas Dick, Tobias Weis, Kallistos Tinnes, Christof Wyrich, Marvin Apel, Sven Software Engineering 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. |
| title | From Developer Pairs to AI Copilots: A Comparative Study on Knowledge Transfer |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2506.04785 |