一句话：主张把附带性学习显式设计回开发者—AI 智能体交互，提出六条设计原则并实现“会教学”的 SHIELD 多智能体系统。
AI 编码智能体正在重塑软件开发：开发者将大量编码任务委托给自主智能体以提升生产力，但这短路了以往通过费力解决问题获得非正式知识的附带性学习路径。未被练习的技能会悄然退化，开发者可能积累“知识债”——智能体执行的变更开发者无法完全理解，形成开发者层面的技术债。论文主张附带性学习不会自行回归，必须有意设计回开发者—智能体交互中，并提出六条设计原则。基于这些原则，作者实现多智能体系统 SHIELD：其“会教学的智能体”理念复用编码智能体自身推理，在不打断开发者心流的前提下呈现情境化、带外的学习时刻，迈向生产力与学习互补的学习感知开发环境。
AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in pursuit of higher productivity. While the gains are real, they come at the cost of incidental learning. Developers historically acquired informal knowledge through effortful problem-solving, and this has long shaped how software engineering expertise develops. However, with over-reliance on agentic coding, unpracticed skills could atrophy silently over time. As this learning pathway is short-circuited, developers risk accruing Knowledge Debt, a developer-level analogue of Technical Debt, where changes the agent executes that the developer cannot fully understand accrue over time. In this paper, we argue that incidental learning will not re-emerge on its own and must be consciously designed back into developer-agent interactions, and propose six design principles to guide such systems. We then present SHIELD, a multi-agent system grounded in the notion of "agents that teach", that operationalizes these principles by leveraging the AI coding agent's own reasoning to surface contextual, out-of-band learning moments without disrupting developer flow. Through this work, we envision a path toward learning-aware development environments where productivity and learning are complementary, not competing.
@inproceedings{abs-2607-06101,
title = {Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development},
author = {Rohit Mehra and Samdyuti Suri and Prithviraj K. Tagadinamani and Kapil Singi and Vikrant Kaulgud and Adam P. Burden},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834557}
}