Large language models can generate fluent explanations, but effective tutoring requires supporting the learner's thought process, not just delivering content. Metacognitive tutoring targets this gap by prompting planning, monitoring, debugging, and evaluation, and crucially, deciding when to be active versus minimally present, based on learner signals and trajectory. We introduce MetaCLASS, a learning-science grounded framework that formulates metacognitive tutoring as move selection over 11 interpretable actions aligned to self-regulated learning processes. MetaCLASS uses a two-phase framework that first plans a pedagogical trajectory conditioned on learner profiles (calibration, help-seeking) and then generates natural dialogue consistent with that plan. This yields a dataset of 1,015 conversations (7,711 turns) annotated with turn-level metacognitive labels, and validated for pedagogical contingency and trajectory adherence. We benchmark nine LLMs on predicting the next coach move given the problem and dialogue context. The best model achieves only 43.2\% accuracy, and models exhibit compulsive intervention bias: in turns where effective metacognitive tutoring requires silent (41.7\% of cases), models predict `no intervention' only 4.2\% of the time, while severely over-predicting high-intervention moves. These results show that traditional content-based tutoring ability does not translate to metacognitive tutoring competence, positioning MetaCLASS as a testbed for developing intelligent tutors that promote self-regulated learning.

翻译：大型语言模型能够生成流畅的解释，但有效的辅导不仅需要传递内容，更需要支持学习者的思维过程。元认知辅导通过引导规划、监控、调试和评估来弥补这一不足，其关键在于根据学习者的信号和学习轨迹，决定何时主动介入或保持最低限度的存在。我们提出了MetaCLASS，一个基于学习科学的框架，将元认知辅导形式化为在11种与自我调节学习过程相一致的可解释行动中进行选择。MetaCLASS采用两阶段框架：首先根据学习者特征（校准、求助行为）规划教学轨迹，然后生成符合该计划的自然对话。由此构建了一个包含1,015段对话（7,711轮）的数据集，每轮对话均标注了元认知标签，并在教学连续性和轨迹一致性方面进行了验证。我们在给定问题和对话上下文的情况下，对九种大型语言模型预测下一辅导行动的准确性进行了基准测试。最佳模型的准确率仅为43.2%，且模型表现出强迫性干预偏差：在有效元认知辅导需要保持沉默的轮次中（占41.7%的案例），模型预测“无干预”的比例仅为4.2%，同时严重过度预测高干预行动。这些结果表明，传统的基于内容的辅导能力并不能转化为元认知辅导能力，这使MetaCLASS成为开发促进自我调节学习的智能辅导系统的测试平台。