AdaTutor：通过教学策略选择实现自适应辅导
AdaTutor: Adaptive Tutoring through Pedagogical Strategy Selection
AI 导读
研究者提出 Comparative Pedagogical Supervision（CPS）训练框架，让辅导模型学习为学生选择最优教学策略与反馈。在数学和科学推理数据集上，经过五轮辅导后 CPS 超过最强固定策略基线。学到的策略选择可跨数据集迁移，还能指导基于 API 的独立辅导模型。
正文 · 原文
Abstract:Effective tutoring requires determining not only what information to provide, but also which form of assistance to deliver. A tutor may address the same student error using various pedagogical strategies, adapting its approach as the interaction progresses. We introduce Comparative Pedagogical Supervision (CPS), a training framework to learn to select the optimal strategy and feedback for student learning. We evaluate CPS on math and science reasoning datasets. After five tutoring turns, CPS outperforms the strongest fixed-strategy baselines. The learned tutor transfers across datasets, and its strategy selection can also inform a separate API-based tutor.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.34659 [cs.AI] |
| (or arXiv:2610.34659v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34659 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rajeev Bhatt Ambati [view email]
[v1]
Mon, 26 Oct 2026 00:44:29 UTC (8,941 KB)
来源：arXiv cs.AI · arxiv.org