一句话：首个眼动追踪研究，揭示生成式 AI 辅助如何改变新手程序员在代码摘要时的注意力分配与参与深度。
生成式 AI 工具正在改变软件开发实践，但学生对其过度依赖可能导致基础软件技能的退化。本文针对这一问题，开展了首个眼动追踪研究，考察生成式 AI 如何影响新手程序员在代码摘要任务中的代码理解过程。研究通过眼动数据分析了 AI 辅助下程序员对具体代码元素（如参数、循环、方法调用）的注视位置、注视频率，以及在不同语义类别上的参与深度。结果显示，AI 辅助显著改变了程序员的注意力模式；同时在各个经验水平上，AI 辅助都使摘要长度一致变长，但对主观评价与自动化度量的摘要质量均无显著影响。研究还发现经验较少的新手更倾向于直接请求摘要，而较少使用代码澄清与摘要评估这两类交互方式，说明在软件工程教育中需要加强 AI 素养与负责任使用工具的教学。
Generative AI tools are transforming software development. While these tools offer benefits for developers, there are growing concerns regarding their use. One of the main concerns is that students’ over-reliance on generative AI can lead to the erosion of foundational software development skills. In this paper, we present the first eye-tracking study investigating how generative AI affects novice programmers’ code comprehension during code summarization tasks. Our findings reveal that AI assistance shifts where and how often programmers focus on specific code elements, as well as the depth of their engagement across semantic categories such as arguments, loops, and method calls. AI assistance also led to consistently longer summaries across experience levels, even though it did not significantly affect perceived or automated measures of summary quality. Additionally, we also observed that the less experienced novices tended to use direct summary requests as opposed to code clarification and summary evaluations, highlighting the need to teach AI literacy and responsible tool use in software engineering education.
@inproceedings{paperbot11992,
title = {Beyond the Prompt: How Novices Engage with AI During Code Summarization},
author = {Suad Mohamed and Abdullah Parvin and Najma Ismail and Kimberly Amaya and Esteban Parra and Michael Oliver},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786580.3786961}
}