arXiv:2506.04920v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them inc...
arXiv:2608.22993v1 Announce Type: new Abstract: Students increasingly use LLMs as tutors for coursework and problem solving. Little is known about the level of assistance LLMs provide when students u...
arXiv:2605.14322v4 Announce Type: replace Abstract: Language agents are increasingly deployed in professional workflows, yet tutoring remains a high-stakes capability that existing evaluations only p...
RegulaTutor is a theory-informed framework for long‑term personalized tutoring that links a learner’s historical evidence to instructional support. Guided by self‑regulated learning research, it uses a cognitive, affective, metacognitive, and motivational (CAMM) framework to derive evidence‑supported learner interpretations and teaching policies that are updated as new observations arrive. The framework includes PairRoute, an offline refinement procedure that distinguishes harness, model, and mixed failures, proposes targeted harness revisions, and constructs stage‑level supervision for confirmed model failures, improving historical‑evidence accuracy, learner diagnosis, and teaching quality across evaluated model configurations.
arXiv:2608. 03952v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-language (ESL) learners.
arXiv:2607. 03303v1 Announce Type: new Abstract: While Large Language Models (LLMs) can provide personalized support in learning, several studies have raised concerns regarding their use in education.
arXiv:2609.28470v1 Announce Type: new Abstract: Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advanc...
arXiv:2608. 07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers.
The paper introduces Universal Textual Teaching (UTT), a parameter‑update‑free framework that distills knowledge gaps between a Teacher and Student large language model into a reusable natural‑language artifact called a Primer. UTT identifies representative gap cases, then iteratively refines the Primer through a cycle of student attempts, prompter‑generated teaching instructions, teacher demonstrations, and synthesizer consolidation. Experiments on math (Omni‑MATH‑2) and code generation (KernelBench) show significant accuracy gains, outperforming prompt engineering and parameter‑based knowledge distillation, and the Primer generalizes across different Teacher‑Student pairs.
arXiv:2608. 05411v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as AI tutors, but a correct answer is not always a pedagogically appropriate one.
arXiv:2608. 11259v1 Announce Type: cross Abstract: Many AI tutors leverage large language models (LLMs) today.
PEARL is a framework that trains Socratic tutoring agents using pedagogically aligned reinforcement learning. It introduces a controllable student simulator to model diverse cognitive states, a reward model that jointly evaluates pedagogical quality and correctness, and a stable multi‑objective RL approach to balance competing tutoring goals. Experiments demonstrate that PEARL competes with both open‑source tutoring systems and leading proprietary LLMs.