发表机构
National Institute of Education, Nanyang Technological University; School of Computer Science and Engineering, Nanyang Technological University; School of Art, Design and Media, Nanyang Technological University; College of Computing and Data Science, Nanyang Technological University; School of Information Engineering, Chang’an University（南洋理工大学国立教育学院; 南洋理工大学计算机科学与工程学院; 南洋理工大学艺术设计与媒体学院; 南洋理工大学计算与数据科学学院; 长安大学信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对编码助手降低元认知参与的问题，提出保留元认知需求原则，并实现CoMeT导师，其根据学习者决策表现升级或消退支持，实验表明在保持需求的同时减少挫败感。
AI 中文摘要
编码助手提高了任务表现，但学习者计划与监控减少。通常的修复方法——减少提供信息——混淆了两件事：系统承担的工作量（认知负荷）和学习者在帮助到达前必须做出的决定（元认知需求）。我们的原则，即保留元认知需求，保持后者恒定而让前者变化。CoMeT实现了这一原则：当学习者在决策点失败时支持升级，并在接受支持后消退。在受试者内设计中，131名成人学习者使用CoMeT、一个不受限制的助手和一个仅提问的导师完成三项Python任务。CoMeT匹配了仅提问导师的需求，交付工件次数是助手的的两倍，并且比仅提问导师更少让学习者受挫，而委派和负荷不变。学习者经常不回答。当学习者的回合在支持下处理决策时，消退得以维持，CoMeT在十六个会话中有一个完全交出答案，而仅提问导师为六分之一。
英文摘要
Coding assistants raise task performance, but learners plan and monitor less. Giving less away, the usual fix, conflates two things: how much work a system carries (cognitive load) and what the learner must decide before help arrives (metacognitive demand). Our principle, preserved metacognitive demand, holds the second constant and lets the first vary. CoMeT implements it: support rises when a learner fails at a decision point and fades on take-up. Within subjects, 131 adult learners used CoMeT, an unrestricted assistant and a question-only tutor on three Python tasks. CoMeT matched the question-only tutor's demand, delivered artifacts twice as often as the assistant, and frustrated learners less than the question-only tutor, with delegation and load unchanged. Learners often did not answer. Fading held when their turn addressed the decision under support, and CoMeT surrendered the full answer in one session in sixteen, against one in six for the question-only tutor.
