一句话：用两年遥测与问卷揭示 AI 编程助手对开发者日常工作流的长期实际影响。
AI 编程助手已迅速成为专业 IDE 的常备功能，但其对日常开发的长期影响仍不清楚；既有研究多聚焦短期使用或自述感知。本文以混合方法研究 IDE 中的 AI 采纳：结合 800 名开发者为期两年的细粒度遥测数据与 62 名从业者的问卷调查，从生产力、代码质量、代码编辑、代码复用和上下文切换五个维度分析工作流变化。遥测显示，AI 用户产出显著更多代码，但删除的代码也显著更多；而问卷受访者报告了生产力提升，并认为其他维度变化甚微。作者据此讨论了软件工作流的“静默重构”，并为未来 AI 增强工具的设计提出启示。
AI‑powered coding assistants are rapidly becoming fixtures in professional IDEs, yet their sustained influence on everyday development remains poorly understood. Prior research has focused on short-term use or self-reported perceptions, leaving open questions about how sustained AI use reshapes actual daily coding practices in the long term. We address this gap with a mixed-method study of AI adoption in IDEs, combining longitudinal two-year fine-grained telemetry from 800 developers with a survey of 62 professionals. We analyze five dimensions of workflow change: productivity, code quality, code editing, code reuse, and context switching. Telemetry reveals that AI users produce substantially more code but also delete significantly more. Meanwhile, survey respondents report productivity gains and perceive minimal changes in other dimensions. Our results offer empirical insights into the silent restructuring of software workflows and provide implications for designing future AI-augmented tooling.
@inproceedings{abs-2601-10258,
title = {Evolving with AI: A Longitudinal Analysis of Developer Logs},
author = {Agnia Sergeyuk and Eric Huang and Dariia Karaeva and Anastasiia Serova and Yaroslav Golubev and Iftekhar Ahmed},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787811}
}