AI 中文总结
针对人工智能编码代理发展下学生和从业者对自身代码理解存疑的问题，开发个性化探测谜题（$p^3$）方法，经云计算课程测试，该方法能识别理解差距，谜题自动生成、耗时短，后续要关联结果与代码理解并嵌入审查流程。
AI 中文摘要
人工智能编码代理的快速发展与普及，意味着不能假定软件工程专业的学生和从业者理解自己的代码，这存在学术诚信和职业责任风险。我们开发了名为个性化探测谜题（$p^3$）的方法来评估学生对自身代码的理解，并在研究生水平的云计算课程中进行测试。初步研究表明，$p^3$有助于识别学生对自身代码理解中的潜在差距。谜题自动生成、异步管理且几分钟内即可完成。未来工作需将谜题结果与代码理解相关联，并将$p^3$嵌入专业代码审查流程。
英文摘要
The rapid development and popularization of AI-enabled coding agents have meant software engineering students and professionals cannot be assumed to understand their own code, which risks academic integrity and professional accountability. We developed a method called Personalized Probing Puzzles ($p^3$) to evaluate students' understanding of their own code, and tested $p^3$ in a graduate-level cloud computing course. Our pilot study shows that $p^3$ can help identify potential gaps in students' understanding of their own code. The puzzles are automatically generated, asynchronously administered, and finished in minutes. Future work is needed to correlate puzzle results with code understanding and to embed $p^3$ in a professional code review process.
Comments6 pages, 3 figures, ECTEL 2026
