🏷️ ai-tutoring

> **Synthesis:** Udeshi et al. (2026), the team behind **Khanmigo** (Khan Academy's K-12 AI tutor, launched 2023), describe the metrics they use to measure AI tutoring quality and student engagement, …

2026-08-13 · intelligent-tutoring, k-12, llm, personalized-learning, efficacy-study

> **Trust in AI** — the willingness of learners and educators to rely on AI systems for learning, judgment, and decision-making. Trust is a precondition for effective use of AI in education, but it is…

2026-08-13 · trust, ai-literacy, social-robots, human-robot-interaction, epistemic-trust

> **Synthesis:** This pilot study (N = 22 STEM higher-education students) evaluates AI-generated interactive fiction as an educational medium. Narrative clarity and length acceptance rated positively,…

2026-08-12 · generative-ai, student-experience, engagement-metrics, curriculum-design, higher-ed

> 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, intelligent-tutoring, scaffolding, math-education

> 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, math-education

> **Synthesis:** This study introduces a Digital Interactions Quality (DigIQ) framework and scale as a protocol to observe and index the quality of interactions and experiences involving digital techn…

2026-08-10 · ai-education, educational-technology, edtech-platform, evaluation, efficacy-study

> **Synthesis:** This study examines the critical influence of technical and structural factors on learner Engagement, Retention and Inclusivity (ERI) in MOOCs and other large-scale online learning pl…

2026-08-10 · engagement-metrics, ai-education, educational-technology, edtech-platform, evaluation

> **Synthesis:** This paper addresses concerns that students use GenAI to submit texts they do not understand, adopting an assessment validity lens. It proposes Coauthorship Integrity as a new concept…

2026-08-10 · generative-ai, assessment, conversational-agents, assessment-validity, academic-integrity

> **Synthesis:** Based on mastery learning theory, this study employed a quasi-experimental design to examine how an AI chatbot-supported cooperative flipped classroom influences students' collaborati…

2026-08-10 · self-regulated-learning, collaborative-learning, chatbot, epistemic-agency, ai-education

> **Synthesis:** This study explores the impact of robot-LLM integration on collaborative creative writing, focusing on how embodiment and AI creativity influence creative output. With 150 undergradua…

2026-08-10 · higher-ed, collaborative-learning, engagement-metrics, creativity, ai-education

> **Synthesis:** Grounded in social presence theory, this study introduces the concept of identity anthropomorphism and adopts multimodal learning analytics (MMLA) combining questionnaires, EEG and ey…

2026-08-10 · affective-computing, agent, learning-analytics, multimodal, ai-education

> **Synthesis:** Two experiments examined how avatar race, gender, and age shape trust in AI-mediated education. Study 1 (N=102) used a within-subjects laboratory design; Study 2 (N=294) adopted a bet…

2026-08-10 · algorithmic-bias, agent, language-learning, epistemic-agency, ai-education

> **Synthesis:** Emotion regulation has been recognized as a key factor affecting students' academic success. This study proposed a self-determination theory (SDT)-based emotional agent framework, imp…

2026-08-10 · affective-computing, ai-education, educational-technology, edtech-platform, evaluation

> **Synthesis:** This systematic scoping review examines the use of GenAI to support the teaching of computational thinking skills. Results reveal a young but rapidly growing research field, with most…

2026-08-10 · generative-ai, higher-ed, computational-thinking, systematic-review, design-guidelines

> **Synthesis:** This four-year comparative study presents results of implementing a Generative-AI Interactive Textbook built on GPT-4, integrated into an Electrical Engineering course. With a sample …

2026-08-10 · generative-ai, assessment, equity, ai-education, educational-technology

> **Synthesis:** This study compares the pedagogical effects on students' design thinking and students' perceptions of feedback systems by GenAI and human instructors. A within-class randomized experi…

2026-08-10 · generative-ai, feedback-design, higher-ed, design-thinking, privacy

> **Synthesis:** This paper presents a scoping review of learning-to-learn (L2L) definitions within pedagogical and psychological literature, identifying 21 relevant publications via PRISMA-ScR. It pr…

2026-08-10 · generative-ai, higher-ed, self-regulated-learning, language-learning, systematic-review

> **Synthesis:** This study challenges the assumption that emotional design in educational AI provides universal benefits, investigating when, for whom and how it impacts L2 vocabulary learning. A qua…

2026-08-10 · affective-computing, language-learning, ai-education, educational-technology, edtech-platform

> **Synthesis:** This study investigated different collaboration modes and how they interact with competition to influence computational thinking learning, group metacognition and in-game behaviours. …

2026-08-10 · computational-thinking, collaborative-learning, ai-education, educational-technology, edtech-platform

> **Synthesis:** Large language model (LLM) tutors are being deployed in introductory physics courses at a scale that produces transcript corpora far larger than traditional qualitative coding can abs…

2026-08-10 · physics-education, socratic-method, discourse-analysis, llm, higher-ed

> **Synthesis:** MacCallum, Parsons, and Mohaghegh (2026) report on a three-round Delphi study that created the Scaffolded AI Literacy (SAIL) framework — a broadly applicable, age-agnostic framework f…

2026-08-10 · ai-literacy, curriculum-design, digital-divide, scaffolding, ai-education

> **Synthesis:** This study examined the effects of pedagogical agents (real vs. virtual) and metaphorical design on learners' performance, attention, comprehension, and psychological distance in a 2x…

2026-08-10 · agent, ai-education, educational-technology, edtech-platform, evaluation

> **Synthesis:** This study employed a three-layer analytical method combining cluster analysis, content analysis and complex network analysis to investigate how socially shared regulation of learning…

2026-08-10 · higher-ed, self-regulated-learning, collaborative-learning, ai-education, educational-technology

> **Synthesis:** By adopting the Will, Skill, Tool (WST) model, this study explores how EMI students' intentions to use GenAI for academic writing are shaped by AI-specific variables. Survey data from…

2026-08-10 · generative-ai, ai-literacy, higher-ed, policy, technology-adoption

> **Synthesis:** TACT (Taxonomy-Aligned Conversational Tutor) presents a human-grounded framework for training and evaluating pedagogically adaptive ESL tutors powered by [[llm|LLMs]]. Built on a Tuto…

2026-08-09 · tutoring, tutoring-systems, scaffolding, adaptive-learning, llm

> **AI Education** — the broad field encompassing both AI in education (using AI to teach) and AI literacy (teaching about AI). As the wiki's umbrella concept, AI education connects instructional tech…

2026-08-09 · ai-literacy, generative-ai, llm, higher-ed, k-12

> **Feedback loop** — the cyclical process where AI systems assess student work, deliver feedback, observe the student's response, and adapt subsequent instruction. Effective feedback loops close the …

2026-08-09 · formative-assessment, ai-feedback-quality, automated-grading, scaffolding, self-regulated-learning

> **Generative AI** — AI systems capable of producing text, code, images, and other content, most prominently large language models like GPT-4 and Claude. Generative AI is the technology driving the c…

2026-08-09 · llm, prompt-engineering, rag, ai-literacy, over-reliance

> **Intelligent Tutoring Systems (ITS)** — a well-established subfield of AI in education that uses AI to model student knowledge, adapt instruction, and provide personalized feedback, typically throu…

2026-08-09 · ai-education, adaptive-learning, scaffolding, student-modeling, knowledge-tracing

> **Large Language Models (LLMs)** — neural network models trained on vast text corpora that generate human-like text, powering most modern AI in education applications. LLMs are the computational bac…

2026-08-09 · generative-ai, prompt-engineering, rag, hallucination-risk, pedagogical-safety

> **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 · math-education, stem-education, intelligent-tutoring, k-12, generative-ai

> **Physics Education** — the study of how students learn physics and how to teach it more effectively, spanning Socratic AI tutoring, computational thinking assessment, student trust and AI adoption …

2026-08-09 · physics-education, stem-education, generative-ai, higher-ed, student-experience

> **RAG (Retrieval-Augmented Generation)** — an AI architecture that combines information retrieval with text generation, allowing LLMs to ground responses in external knowledge sources rather than re…

2026-08-09 · llm, generative-ai, hallucination-risk, knowledge-graph, edtech-platform

> **Socratic Method** — a pedagogical approach rooted in guided questioning and dialogue rather than direct instruction, now being adapted for generative AI tutoring systems. In AI in education, the S…

2026-08-09 · ai-education, generative-ai, higher-ed, student-experience, scaffolding

> **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, math-education, physics-education, computational-thinking, k-12

> **Teacher role** — how AI reshapes the work, identity, and agency of educators. With 50+ articles examining this dimension, the wiki documents a fundamental transformation: from sole knowledge autho…

2026-08-09 · faculty-development, teacher-ai-competency, ai-literacy, 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

> **Lan Anh Do, Hanling Jiang, Shuchin Aeron, Ayanna K. Thomas** — CogSci 2026 (accepted full paper).…

2026-08-03 · llm, collaborative-learning, learning-analytics, student-ai-interaction, nlp-education

> **Ilya Mikhelson** — Submitted to Computers and Education: Artificial Intelligence (2026).…

2026-08-03 · llm, generative-ai, assessment, automated-grading, assessment-validity

Presents **StructRAG**, a pattern-aware framework that improves how AI tutoring systems interpret **complex engineering diagrams** (circuit schematics, network topologies, block flowcharts) in STEM. C…

2026-08-03 · intelligent-tutoring, stem-education, llm, generative-ai, automated-grading

> **ProPACT** (Proactive AI-Driven Adaptive Collaborative Tutor) is an AI-driven adaptive tutoring system for pair programming that **treats collaboration itself as the object of instruction.** Unlike…

2026-07-29 · pair-programming, collaborative-learning, cs-education, adaptive-learning-systems, rag

> **SafeTutors** is a benchmark that jointly evaluates safety and pedagogy in AI tutoring systems across mathematics, physics, and chemistry. It argues that **tutoring safety is fundamentally differen…

2026-07-29 · pedagogical-safety, k-12, llm, scaffolding, regulation

> **Interpretable Knowledge Tracing** — A novel framework for dialogue-based Knowledge Tracing that explicitly models both student ability and tutor-turn difficulty using Item Response Theory, produci…

2026-07-29 · knowledge-tracing, interpretability, student-modeling, cold-start-knowledge-tracing-safeinsights, item-response-theory

> **PersonaVLM** introduces an agent framework for long-term personalization of multimodal LLMs, enabling AI tutors to remember, reason about, and align with a learner's evolving preferences across hu…

2026-07-29 · personalized-learning, intelligent-tutoring, student-modeling, llm, affective-tutoring

> **Stanford Evidence Base: AI in K-12 Education** — A 2026 systematic review from the Stanford SCALE Initiative analyzing 818 papers on AI in K-12 education. The central finding is stark: only 20 stu…

2026-07-29 · k-12, ai-literacy, evidence, zone-of-proximal-development, k-12-ai-education

> **The Multimodal Interference Effect** describes a systemic accuracy drop when LLMs encounter image-rich STEM problems: from ~96% on text-only physics problems to ~74% on multimodal ones. A simple t…

2026-07-29 · intelligent-tutoring, multimodal, socratic-method, stem-education, llm

MedGame transforms static clinical cases into structured, executable storytelling games for medical education, moving beyond the localized question-answering and single-turn feedback that characterize…

2026-07-24 · llm, generative-ai, professional-training, engagement-metrics, benchmark

Graf et al. (2026) identify a new challenge in collaborative programming education: AI use is now an invisible yet consequential dimension of collaboration, and partners often misread ability and effo…

2026-06-23 · student-experience, cs-education, collaborative-ai-tutoring, over-reliance, higher-ed

This study embedded undisclosed AI agents as teammates in synchronous text-based group interactions across analytical, creative, and ethical tasks with 786 participants making 1,572 identity judgments…

2026-05-25 · ai-literacy, over-reliance, student-experience, llm, affective-computing

Automated grading systems have enabled scalable assessment for many response types, but handwritten mathematics remains a barrier due to the complexity of multi-step solutions. Vision-capable large la…

2026-05-22 · automated-grading, llm, stem-education, higher-ed, efficacy-study

This paper tackles a core ITS challenge: predicting when students will disengage so tutors can intervene before it's too late. It introduces **engagement forecasting** as a supervised prediction task …

2026-05-20 · intelligent-tutoring, learning-analytics, engagement-metrics, k-12, efficacy-study

> Taklif.AI: LLM-Powered Platform for Interest-Based Personalized College Assignments **Kurdya et al. (2026)** — Multiple institutions. arXiv cs.AI.…

2026-05-15 · higher-ed, generative-ai, llm, personalized-learning, edtech-platform

> **Yu, Lu, Si et al. (77 authors, 2026)** — Shanghai Jiao Tong University, SII, GAIR. Open-source benchmark.…

2026-05-11 · benchmark, higher-ed, llm, generative-ai, student-experience

> **Authors:** Eason Chen, Ce Guan, A Elshafiey, Zhonghao Zhao, Joshua Zekeri, Afeez Edeifo Shaibu, Emmanuel Osadebe Prince **Year:** 2026 **Venue:** arXiv (cs.HC) > Mining discourse from Moltbook, a …

2026-05-11 · agentic-ai, benchmark, collaborative-ai-tutoring, engagement-metrics, learning-analytics

**Cognitive Agent Compilation (CAC)** is a framework that uses a strong teacher LLM to compile problem-solving knowledge into an explicit, inspectable target agent. Unlike end-to-end LLM tutoring appr…

2026-05-11 · intelligent-tutoring, llm, adaptive-learning, personalized-learning, pedagogical-llm-training

Most AI-based educational tools adopt a one-on-one tutoring paradigm, pairing a single LLM with a single learner. Yet decades of learning science — from Vygotsky's Zone of Proximal Development to Band…

2026-05-11 · llm, intelligent-tutoring, scaffolding, student-experience, collaborative-ai-tutoring

> A framework for evaluating AI tutoring systems that extends beyond pedagogical quality of feedback to measure what students actually *do* with that feedback — whether they act on it and whether they…

2026-05-09 · intelligent-tutoring, efficacy-study, higher-ed, benchmark, engagement-metrics

> A pedagogical model where human mentors and AI tools jointly support student learning in project-based contexts. Human mentors provide conceptual guidance, debugging, and problem formulation support…

2026-05-09 · stem-education, k-12, higher-ed, active-learning, scaffolding

> An instructional approach that deliberately leverages AI errors, hallucinations, and limitations as teaching tools to foster higher-order thinking. Rather than viewing AI mistakes as failures to be …

2026-05-09 · higher-ed, ai-literacy, metacognition, stem-education, active-learning

> A web-based writing environment that inverts the AI-tutoring paradigm: rather than generating improved text for students, Prober.ai constrains an LLM to ask only targeted inquiry-based questions abo…

2026-05-09 · writing-education, scaffolding, ai-literacy, higher-ed, formative-assessment

> AI coding assistants proliferate rapidly, but pedagogical frameworks for learning them remain scarce — a paradox at the heart of agentic coding education. > Using agentic AI workflows (Claude Code) …

2026-05-08 · agentic-ai, generative-ai, higher-ed, scaffolding, stem-education

> **From Prototype to Classroom** (Elhaimeur & Chrisochoides, 2026) describes a tutoring system for quantum computing that bridges the gap between dense mathematical formalism and limited qualified in…

2026-05-08 · adaptive-learning, higher-ed, intelligent-tutoring, knowledge-tracing, stem-education

> Peer feedback develops critical reflection and evaluative judgment, yet: > Student peer feedback is often superficial or inconsistent. **AICoFe** (AI-based Collaborative Feedback) uses a multi-LLM p…

2026-05-07 · edtech-platform, feedback-loop, formative-assessment, teacher-role, higher-ed

> Gonnermann-Müller, Haase & Leins (2026) evaluate whether **LLM-generated student personas simulating ADHD profiles** maintain stable and realistic behavioral patterns over time. This addresses a cri…

2026-05-07 · llm, student-experience, ai-education, generative-ai, benchmark

> **Transfer of Learning** — the extent to which knowledge or skills acquired in one context (e.g., practice with an AI tool) persist and apply in a different context (e.g., independent performance wi…

2026-05-07 · transfer-of-learning, metacognition, cognitive-load-theory, desirable-difficulties, k-12