AI Ed Researcher

Authors: Yang Wu, Rujing Yao, Tong Zhang, Yufei Shi, Zhuoren Jiang, Zhushan Li, Xiaozhong Liu

Abstract: Large Language Models (LLMs) are increasingly integrated into intelligent tutoring systems to provide human-like and adaptive instruction. However, most existing approaches fail to capture how students’ knowledge evolves dynamically across their proficiencies, conceptual gaps, and forgetting patterns. This challenge is particularly acute in mathematics tutoring, where effective instruction requires fine-grained scaffolding precisely calibrated to each student’s mastery level and cognitive retention. To address this issue, we propose TASA (Teaching According to Students’ Aptitude), a student-aware tutoring framework that integrates persona, memory, and forgetting dynamics for personalized mathematics learning. Specifically, TASA maintains a structured student persona capturing proficiency profiles and an event memory recording prior learning interactions. By incorporating a continuous forgetting curve with knowledge tracing, TASA dynamically updates each student’s mastery state and generates contextually appropriate, difficulty-calibrated questions and explanations. Empirical results demonstrate that TASA achieves superior learning outcomes and more adaptive tutoring behavior compared to representative baselines, underscoring the importance of modeling temporal forgetting and learner profiles in LLM-based tutoring systems.

Link: https://arxiv.org/abs/2511.15163

Authors: Biaojie Zeng, Min Zhang, Juan Zhou, Fengrui Liu, Ruiyang Huang, Xin Lin

Abstract: Large language models (LLMs) often make reasoning errors when solving mathematical problems, and how to automatically detect and correct these errors has become an important research direction. However, existing approaches \textit{mainly focus on self-correction within the model}, which falls short of the “teacher-style“ correction required in educational settings, \textit{i.e.}, systematically guiding and revising a student’s problem-solving process. To address this gap, we propose \texttt{SMRC} (\textit{\underline{S}tudent \underline{M}athematical \underline{R}easoning \underline{C}orrection}), a novel method that aligns LLMs with student reasoning. Specifically, \texttt{SMRC} formulates student reasoning as a multi-step sequential decision problem and introduces Monte Carlo Tree Search (MCTS) to explore optimal correction paths. To reduce the cost of the annotating process-level rewards, we leverage breadth-first search (BFS) guided by LLMs and final-answer evaluation to generate reward signals, which are then distributed across intermediate reasoning steps via a back-propagation mechanism, enabling fine-grained process supervision. Additionally, we construct a benchmark for high school mathematics, MSEB (Multi-Solution Error Benchmark), consisting of 158 instances that include problem statements, student solutions, and correct reasoning steps. We further propose a dual evaluation protocol centered on \textbf{solution accuracy} and \textbf{correct-step retention}, offering a comprehensive measure of educational applicability. Experiments demonstrate that \texttt{SMRC} significantly outperforms existing methods on two public datasets (ProcessBench and MR-GSM8K) and our MSEB in terms of effectiveness and overall performance. The code and data are available atthis https URL.

Link: https://arxiv.org/abs/2511.14684

Authors: Kovan Mzwri(1), Márta Turcsányi-Szabo(2) ((1) Doctoral School of Informatics, Eötvös Loránd University, Budapest, Hungary, (2) Department of Media & Educational Technology, Faculty of Informatics, Eötvös Loránd University, Budapest, Hungary)

Abstract: Integration of Large Language Models (LLMs) with Learning Management Systems (LMSs) can enhance task automation and accessibility in education. However, hallucination where LLMs generate inaccurate or misleading information remains a challenge. This study introduces the Dynamic Course Content Integration (DCCI) mechanism, which dynamically retrieves course content from Canvas LMS and structures it within an LLM’s context window via prompt engineering, enabling the LLM-powered assistant, Ask ME, to deliver context-aware, curriculum-aligned responses while mitigating hallucinations. A mixed-methods pilot study grounded in Self-Determination Theory (autonomy, competence) and the Technology Acceptance Model (perceived usefulness, ease of use) evaluated DCCI’s effectiveness with 120 first-year programming students at Eötvös Loránd University. The course focused on foundational programming patterns in C#, including writing program specifications. We analyzed 14,746 logged interactions and a post-course survey completed by 101 students. User satisfaction was measured via a 5-point Likert scale (turn-level ratings), while the survey assessed usability, engagement, and ethical concerns. Results indicated high satisfaction (mean 4.65/5) and strong recognition of Ask ME’s ability to provide timely, contextually relevant answers to administrative and course-related queries. 78.06% agreed that Ask ME’s Canvas integration reduced platform switching, improving usability, engagement, comprehension, and topic exploration. Many students reported reduced hesitation to ask questions and increased motivation for self-directed learning, though concerns about over-reliance on AI and reduced student-teacher interaction emerged. This study demonstrates that DCCI enhances LLM reliability, student satisfaction, and engagement in AI-driven educational automation, while highlighting the importance of balancing

Link: https://arxiv.org/abs/2504.03966

Authors: Jieun Han, Daniel Lee, Haneul Yoo, Jinsung Yoon, Junyeong Park, Suin Kim, So-Yeon Ahn, Alice Oh

Abstract: Personalized learning has gained attention in English as a Foreign Language (EFL) education, where engagement and motivation play crucial roles in reading comprehension. We propose a novel approach to generating personalized English reading comprehension tests tailored to students’ interests. We develop a structured content transcreation pipeline using OpenAI’s gpt-4o, where we start with the RACE-C dataset, and generate new passages and multiple-choice reading comprehension questions that are linguistically similar to the original passages but semantically aligned with individual learners’ interests. Our methodology integrates topic extraction, question classification based on Bloom’s taxonomy, linguistic feature analysis, and content transcreation to enhance student engagement. We conduct a controlled experiment with EFL learners in South Korea to examine the impact of interest-aligned reading materials on comprehension and motivation. Our results show students learning with personalized reading passages demonstrate improved comprehension and motivation retention compared to those learning with non-personalized materials.

Link: https://arxiv.org/abs/2511.09135

Authors: Rahul R. Divekar, Sophia Guerra, Lisette Gonzalez, Natasha Boos

Abstract: While Large Language Models (LLMs) have transformed the user interface for learning, moving from keyword search to natural language dialogue, their impact on educational outcomes remains unclear. We present a controlled study (N=20) that directly compares the learning interaction and outcomes between LLM and search-based interfaces. We found that although LLMs elicit richer and nuanced interactions from a learner, they do not produce broadly better learning outcomes. In this paper, we explore this the “Interaction-Outcome Paradox.” To explain this, we discuss the concept of a cognitive shift: the locus of student effort moves from finding and synthesizing disparate sources (search) to a more self-aware identification and articulation of their knowledge gaps and strategies to bridge those gaps (LLMs). This insight provides a new lens for evaluating educational technologies, suggesting that the future of learning tools lies not in simply enriching interaction, but in designing systems that scaffold productive cognitive work by leveraging this student expressiveness.

Link: https://arxiv.org/abs/2511.09458