🏷️ math-education

> Pardos & Bhandari (2024) report a randomized efficacy study (N=274) comparing ChatGPT-generated hints to human tutor-authored hints and a no-help control across four mathematics subject areas. Only …

2026-08-12 · generative-ai, llm, ai-tutoring, intelligent-tutoring, scaffolding

> OATutor (Open Adaptive Tutor) is the first open-source adaptive tutoring system built on Intelligent Tutoring System (ITS) principles, developed at UC Berkeley's CAHL Lab. It combines an MIT-license…

2026-08-12 · intelligent-tutoring, adaptive-learning, open-source, knowledge-tracing, higher-ed

> **Math Education** — the study of how students learn mathematics and how AI can support mathematics teaching, spanning affective tutoring, cognitive diagnosis from handwritten work, productive strug…

2026-08-09 · stem-education, ai-tutoring, intelligent-tutoring, k-12, generative-ai

> **STEM Education** — science, technology, engineering, and mathematics education is the most common domain for AI in education research in the wiki. STEM's structured knowledge, clear right/wrong an…

2026-08-09 · cs-education, physics-education, computational-thinking, k-12, higher-ed

> **Synthesis:** Zhang et al. (2026) introduce TutorMoments, a replay-based evaluation framework that tests whether LM tutors adapt their pedagogical actions to context — scaffolding when support is n…

2026-08-08 · intelligent-tutoring, scaffolding, llm, llm-evaluation, k-12

> **Synthesis:** Examines AI-powered personalized learning in elementary fraction instruction through a systematic review, quantitative study (N=120), and qualitative teacher interviews. Found that AI…

2026-08-06 · ai-generated-content, personalized-learning, k-12, adaptive-learning, student-experience

> **Synthesis:** A three-semester, 999-student analysis of hint usage in a K-12 mathematics ITS finds that two simple, interpretable indicators—premature hint requests and superficial hint reading—are…

2026-08-06 · intelligent-tutoring, learning-analytics, hint-systems, k-12, gaming-the-system

> **MathBuddy: Affective Math Tutoring** — EMNLP 2025 Demo. An emotionally aware LLM-powered mathematics tutor that dynamically models student emotions from both conversational text and facial express…

2026-07-29 · affective-computing, intelligent-tutoring, k-12, pedagogical-llm-training, affective-tutoring

This study probes how sensitive [[llm]] mathematical problem solving is to the surface representation of an item — a question with direct bearing on [[assessment-validity]] when LLMs are used for scor…

2026-07-24 · llm, stem-education, benchmark, assessment-validity, reinforcement-learning

Abdelghani, Kaiser & Murayama (2026) trace how middle and high school students' interactions with AI math tutors evolve over time, identifying a trajectory from superficial prompting ('tell me the ans…

2026-06-30 · ai-literacy, k-12, metacognition, stem-education, student-experience

> **Synthesis:** AI literacy-related domains and AI-TPACK readiness among preservice mathematics teachers: A factor-informed structural equation modelling study…

2026-06-03 · ai-literacy, higher-ed, stem-education, faculty-development

> **Synthesis:** GenAI as a runaway object in higher education: A socio-cultural view on AI-influenced academic practice in mathematics…

2026-06-03 · generative-ai, higher-ed, stem-education, faculty-development, educational-theory

> **MathCog** benchmark (3,036 teacher-annotated diagnostic verdicts, 639 handwritten responses, 18 LLMs): all models severely underperform (macro F1 < 0.5) — over-attributing evidence, overthinking m…

2026-05-31 · ai-ed-evaluation, knowledge-tracing, multimodal, benchmark, human-in-the-loop

Generative AI can help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be **pedagogically meaningful and instructio…

2026-05-12 · teacher-role, stem-education, ai-generated-content, curriculum-design, pedagogy