AI编程助手提升效率却削弱理解，影响代码扩展能力。
(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding
- 对比编码代理与聊天机器人，测试用户理解力差异。
- 代理辅助虽加速任务完成，但降低代码理解度，难以拓展代码。
- 低投入交互方式（如复制粘贴）最损害理解，用户仍偏好便捷工具。
编程代理（如Cursor）通过优化任务完成提升开发者效率，但将用户从编写代码转向提示和审查可能损害其理解力，影响监督、学习与沟通。我们让54名学生使用两种AI系统之一构建网站：一种是编辑用户代码的代理；另一种是用户独立编写或调整通用代码片段的聊天机器人。通过理解测验及无代理情况下扩展代码的任务，结果显示：(1) 虽然代理有助于初始任务完成，但损害用户对代码的理解，无法为其后续扩展做好准备；(2) 低投入的代理交互方式（如复制粘贴提示、自动接受修改）与较低理解度相关；(3) 尽管自评理解力较弱，用户仍更偏好编程代理，因其快速简便。尽管用户在编码流程中保持参与，理解不应被忽视。据此，我们提炼出未来研究方向：减少低效提示、生成可读代码、促进主动参与。
原文摘要 · Abstract (English)
Coding agents (e.g., Cursor) improve developer productivity by optimizing task completion, but shifting users from writing code to prompting and reviewing may harm their understanding, impeding oversight, learning, and communication. To probe this, we have 54 students create a website with one of two AI systems: an agent that edits user code; or a chatbot where users write code alone or adapt generic code snippets. We test understanding via comprehension questions and a task where users extend their code without agents, showing: (1) While agents aid initial task completion, they harm users' code comprehension and thus do not prepare users to extend their code; (2) Low-effort agent interaction types, like copy+paste prompts and auto-accepted edits, are linked with lower comprehension; and (3) Despite self-reported weaker understanding, users still prefer coding agents because they are quick and easy to use. While users stay in the loop for coding workflows, understanding should not be forgotten. Towards this goal, we distill our analyses into future research directions for coding agent developers: dissuading low-effort prompting, creating readable code, and promoting active engagement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。