Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop

arXiv:2610.15692v2 Announce Type: replace 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.

Related

• LLMs learn different forms of metacognition when trained to predict their own accuracy
• BLADE: Better Language Answers through Dialogue and Explanations
• Fast, Slow, and Tool-augmented Thinking for LLMs: A Review

Source: arXiv cs.CL | 2026-10-15