The study analyzes 20,462 student turns from 1,260 sessions with a guided LLM chemistry tutor, identifying 6,630 impasse turns categorized as conceptual errors, expressed uncertainty, or help‑seeking. Three tutoring conditions—baseline, no‑direct‑answer, and guided—were simulated, revealing that the baseline tutor often gave direct answers, the no‑direct‑answer tutor always asked follow‑up questions, and the guided tutor varied its responses based on context. Impasse trajectories showed that each additional impasse turn reduced the likelihood of recovery, while addressing errors became increasingly beneficial compared to repeated scripted questioning.
By Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli, Josh Arens, Ksenia Ionova, Clayton Cohn, Shima Salehi, Rene Kizilcec
arXiv:2509.05346v3 Announce Type: replace
Abstract: While large language models (LLMs) are increasingly being adopted to support personalized learning, there remains limited understanding of how thei...
By Bo Yuan, Jiazi Hu
SafeTutors is a benchmark designed to evaluate both safety and pedagogical effectiveness of AI tutoring systems across mathematics, physics, and chemistry. It introduces a risk taxonomy of 11 harm dimensions and 48 sub‑risks based on learning‑science literature, focusing on issues such as answer over‑disclosure, misconception reinforcement, and loss of scaffolding. The study finds that all tested models exhibit broad harms, that larger scale does not mitigate these issues, and that multi‑turn interactions significantly increase pedagogical failures from 17.7% to 77.8%.
By Rima Hazra, Bikram Ghuku, Ilona Marchenko, Yaroslava Tokarieva, Sayan Layek, Somnath Banerjee, Julia Stoyanovich, Mykola Pechenizkiy
EduDial is a large-scale multi-turn teacher‑student dialogue corpus covering 345 core knowledge points and 34,250 dialogue sessions, designed around Bloom’s taxonomy and ten questioning strategies such as situational, ZPD, and metacognitive questioning. The dataset includes differentiated teaching strategies for students at varying cognitive levels to provide targeted guidance. Using EduDial, the authors trained EduDial‑LLM 32B and introduced an 11‑dimensional evaluation framework that measures teaching quality and content quality, showing that most mainstream LLMs struggle with student‑centered teaching while EduDial‑LLM outperforms all baselines across all metrics.
By Shouang Wei, Min Zhang, Xin Lin, Bo Jiang, Zhongxiang Dai, Kun Kuang
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...
By Suhyeon Lee, Juneha Baek, Jaehyeong Park, Donghyuk Shin
arXiv:2606. 01584v1 Announce Type: cross Abstract: Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback.
By Aitor Arronte Alvarez, Naiyi Xie Fincham
arXiv:2606. 12422v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices.
By Zewei Tian, Alex Liu, Lief Esbenshade, Michael Xiao, Zachary Zhang, Yulia L\'apicus, Thomas Han, Kevin He, Min Sun
arXiv:2607. 01247v1 Announce Type: cross Abstract: Open-ended mathematics exams are valuable because they assess reasoning, proof construction, algorithmic thinking, and communication of intermediate steps.
By Aastha Sapkota, M. G. Sarwar Murshed
The paper introduces Knowledge Tracing Leveraging Problem‑Solving Process (KT‑PSP), a method that incorporates students’ problem‑solving steps to model mathematical proficiency more comprehensively than traditional knowledge tracing. It presents the KT‑PSP‑25 dataset and a new framework, StatusKT, which uses a teacher‑student‑teacher LLM pipeline to extract proficiency indicators, generate responses, and evaluate mastery. Experiments show that StatusKT improves prediction accuracy and offers interpretable explanations by explicitly modeling proficiency.
By Jungyang Park, Suho Kang, Jaewoo Park, Jaehong Kim, Jaewoo Shin, Seonjoon Park, Youngjae Yu
arXiv:2606. 16206v1 Announce Type: new Abstract: Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learning support.
By Junyi Yao, Zihao Zheng, Baichuan Li
arXiv:2606.16206v2 Announce Type: replace
Abstract: Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learni...
By Junyi Yao, Zihao Zheng, Baichuan Li
The study explores whether instruction-tuned large language models (LLMs) can analyze collaborative student sensemaking without task-specific training, and whether adding structured knowledge-state information enhances this analysis. Two mid-size LLMs were evaluated on 23 expert-labeled episodes under various prompting conditions, showing that reasoning-enabled prompts better detect unsuccessful sensemaking and that knowledge-state diagnostics improve agreement with experts. No single configuration outperformed others across all sensemaking dimensions, highlighting the task’s multidimensional nature.
By \"Ozge Alacam, Z\"ubeyde Demet Kirbulut G\"une\c{s}, Funda Ekici, Nurcan Turan-Oluk, Dilay Din\c{c}demir, Hakk{\i} Kaday{\i}f\c{c}{\i}, Sevin\c{c} Nihal Ye\c{s}ilo\u{g}lu, Burcu I\c{s}{\i}k, Halil T\"umay, Sinem Gencer