arXiv AI
Jul 1
What Drives Interactive Improvement from Feedback?
arXiv:2606. 30774v1 Announce Type: new Abstract: We study when natural-language feedback produces improvement beyond the gains obtainable from repeated attempts alone.
Simulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback
Related stories
arXiv Computation and Language
3d ago
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-c...
arXiv Computation and Language
Aug 25
LLM Pedagogical Behavior in AI Tutoring Interactions
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 AI
Sep 24
StudentBench: AI and human tutoring yield equivalent GRE learning gains
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 AI
2d ago
Multi-sourced AI Tutor for Non-Native English Speaker Students
The paper presents a multi‑source Retrieval‑Augmented Generation (RAG) AI tutor designed to help non‑native English speaker (NNES) students in computing courses. It can process questions in foreign languages—currently Mandarin—and give bilingual answers, generate glossaries of technical terms, and translate queries. In tests on 91 Piazza posts, the tutor answered 83.52 % correctly, translated 76.92 % of questions, and produced glossaries for 64.47 % of them.
arXiv AI
Jul 24
AI Assistants Overassist
arXiv:2607. 21306v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as tutors and thought partners, helping users reason through problems.
arXiv AI
Oct 9
Universal Textual Teaching for LLMs
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 AI
Aug 5
TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring
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 AI
Jul 10
DeepTutor: Towards Agentic Personalized Tutoring
arXiv:2604. 26962v3 Announce Type: replace-cross Abstract: Education is one of the most promising real-world applications for Large Language Models (LLMs).
arXiv AI
Jul 8
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
arXiv:2607. 06327v1 Announce Type: cross Abstract: Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English.
arXiv AI
Jul 8
CSTutorBench: Benchmarking Small Language Models as Tutors for Block-Based Programming
arXiv:2607. 05571v1 Announce Type: new Abstract: Large language models are increasingly explored as AI tutors, yet deploying them in K-12 settings raises concerns around privacy, cost, and reliance on proprietary models.
arXiv AI
Aug 25
Evaluating Large Language Models for automatic analysis of teacher simulations
The paper evaluates Large Language Models for automatically analyzing responses in digital teacher simulations. Experiments compare DeBERTaV3 and Llama 3 across zero‑shot, few‑shot, and fine‑tuning settings, revealing that performance varies by characteristic and that Llama 3 consistently outperforms DeBERTaV3, especially when new characteristics must be identified. The findings suggest Llama 3 is preferable for dynamic simulation environments where teacher educators introduce new evaluation criteria.