（非）配对编程：编码智能体提升生产力但损害理解能力
(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding
浏览论文内容
中文总结 AI 辅助
该研究通过54名学生的对照实验，发现编码智能体虽提升生产力但损害用户代码理解，低投入交互加剧该问题，用户仍偏好智能体，同时为开发者提出了优化方向。
中文摘要 AI 辅助
编码智能体（例如Cursor）通过优化任务完成提升开发者生产力，但将用户从编写代码转向提示和审核可能损害其理解能力，阻碍监督、学习和交流。为探究这一点，我们让54名学生使用两种AI系统之一创建网站：一种是编辑用户代码的智能体，另一种是用户自行编写代码或适配通用代码片段的聊天机器人。我们通过理解题和用户在无智能体时扩展代码的任务测试理解能力，结果显示：（1）智能体虽助力初始任务完成，但损害用户的代码理解能力，因此无法让用户做好扩展代码的准备；（2）低投入的智能体交互类型，如复制粘贴提示和自动接受的编辑，与更低的理解能力相关；（3）尽管用户自我报告理解能力较弱，但仍偏好编码智能体，因为它们快速且易用。用户在编码工作流中保持参与的同时，不应忽视理解能力。为此，我们将分析提炼为编码智能体开发者的未来研究方向：劝阻低投入提示、创建可读代码及促进主动参与。
英文摘要
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.
