arXiv：cs.CL· Sayantan Adak, Rima Hazra, Koyel Mukherjee, Digbalay Bose, Somnath Banerjee·· 16 小时前
LLM 辅导真能教会学生吗？一项以过程为中心的辅导闭环综述
Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop
AI 导读
一项以过程为中心的综述梳理了 LLM 辅导从学习者状态推断到教学行动、导师训练、评估与学生模拟的完整链路，指出实现某个辅导组件并不等于它有效或能影响后续环节。结构化研究审计显示，教学评估类研究较多，但学习者条件化干预、人类学习增益、尤其是迁移与延迟保持方面的证据明显薄弱。人类研究给出有条件正面结论：LLM 导师能提升学习，但收益取决于教学结构、学习者投入与学习测量方式。
正文
Abstract:Large language models can produce fluent tu- toring dialogue, but whether they actually help students learn remains unclear. We present a process-centered synthesis of LLM tutoring that follows the path from learner-state infer- ence to pedagogical action, tutor training, eval- uation, and student simulation. This view ex- poses a central gap: implementing a tutoring component does not establish that it works or that its outputs meaningfully affect later stages. A structured study-level audit shows that peda- gogical evaluation is common, while evidence becomes much thinner for learner-conditioned intervention, human learning gains, and espe- cially transfer or delayed retention. Human studies nevertheless provide a conditional posi- tive result: LLM tutors can improve learning, but benefits depend on pedagogical structure, learner engagement, and how learning is mea- sured. We argue that progress requires validat- ing the interfaces between tutoring stages, not only improving individual components.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.15692 [cs.CL] |
| (or arXiv:2610.15692v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15692 arXiv-issued DOI via DataCite |
Submission history
From: Somnath Banerjee [view email]
[v1]
Sun, 11 Oct 2026 15:24:16 UTC (424 KB)
[v2]
Wed, 14 Oct 2026 05:07:43 UTC (427 KB)
来源：arXiv：cs.CL · arxiv.org