🏷️ pedagogical-llm-training

> **Synthesis:** Le, Huynh, Dang, Pham, Nguyen, and Nguyen (2026) develop and evaluate a design-based research (DBR) intervention providing GenAI literacy training for teacher education students. Argu…

2026-08-10 · ai-literacy, teacher-ai-competency, faculty-development, higher-ed, k-12

> **Synthesis:** Chiu (2026) proposes the Human-Centric AI Pedagogy (HCAP) framework, an evolution of the Technological Pedagogical Content Knowledge (TPACK) model designed for the generative AI era. …

2026-08-10 · ai-literacy, teacher-ai-competency, faculty-development, ai-education, ethics

> **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

> **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 · math-education, affective-computing, intelligent-tutoring, k-12, affective-tutoring

> **EduQwen: Pedagogical RL** — A multi-stage optimization strategy combining reinforcement learning (DAPO) and supervised fine-tuning (SFT) to enhance the pedagogical knowledge of open-source LLMs, p…

2026-07-29 · llm, pedagogical-safety, reinforcement-learning, open-source, rag

> **Comprehensive Review of Intelligent Tutoring Systems** — Journal of Computers in Education (2025). A systematic literature review covering 2010–2025 that analyzes the deployment and effectiveness …

2026-07-29 · intelligent-tutoring, literature-review, adaptive-learning, educational-nlp, socratic-questioning

EduGuard is a retrieval-augmented generation (RAG) tutoring framework that directly confronts the safety and pedagogical failures of unrestricted LLM tutors in introductory programming. Unrestricted t…

2026-07-20 · llm, generative-ai, intelligent-tutoring, stem-education, over-reliance

**Gendo Kumoi, Fumie Watanabe, Tota Suko, Takashi Ishida, et al. (2026)** - arXiv preprint (IEEE). arXiv preprint. Kumoi, G., Watanabe, F., Suko, T., Ishida, T., et al. (2026). [A Semi-Automated Syste…

2026-07-15 · llm, generative-ai, personalized-learning, scaffolding, active-learning

> **Jaward Sesay, Yue Yu, Siwei Dong, Yemin Shi, Guangyao Chen, Borje F. Karlsson** (2026). arXiv cs.CL…

2026-06-17 · llm, generative-ai, personalized-learning, higher-ed, intelligent-tutoring

LLM sycophancy creates a feedback loop where user errors propagate into AI advice, degrading outcomes; AI literacy training reduces but doesn't eliminate this contextual sycophantic dependence. This A…

2026-05-19 · llm, generative-ai, ai-literacy, hallucination-risk, student-experience

Codify (also referred to as "AI Tutor") is a web-based [[intelligent-tutoring]] platform for programming education that integrates conversational AI, adaptive assessment, and learning analytics. It le…

2026-05-17 · generative-ai, higher-ed, intelligent-tutoring, llm, programming-its

> Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows **Chen et al. (2026)** — Multiple institutions. Under review.…

2026-05-15 · agentic-ai, benchmark, generative-ai, intelligent-tutoring, llm

> **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

**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, adaptive-learning-systems

> An analysis of 310 AI-generated lesson plans (2,230 individual activities) produced by ChatGPT (GPT-4o), Gemini (1.5 Flash), and Copilot (GPT-4 based) for all 53 Massachusetts eighth-grade civics st…

2026-05-09 · k-12, ai-literacy, teacher-role, formative-assessment, equity

> Key limitations exist in both LLM-based tutoring and conventional Deep Knowledge Tracing (DKT): > Combining neural networks with symbolic educational knowledge for interpretable, data-efficient, and…

2026-05-08 · intelligent-tutoring, learning-analytics, adaptive-learning, pedagogical-safety, mastery-learning

> Boateng et al. (2026) introduce **NSMQ Riddles**, a benchmark of 1.8K scientific and mathematical riddles drawn from 11 years of Ghana's **National Science and Maths Quiz** — a live TV competition f…

2026-05-08 · benchmark, stem-education, k-12, llm, efficacy-study

> A design framework for educational AI systems structured around four agentic paradigms: **reflection**, **planning**, **tool use**, and **multi-agent collaboration**. Proposed by Kamalov et al. (202…

2026-05-07 · agentic-ai, ai-education, benchmark, intelligent-tutoring, human-in-the-loop-ai

> Zerkouk, Mihoubi & Chikhaoui (2025) systematically analyzed qualified studies from 2010–2025 across: > A comprehensive systematic review of AI-based Intelligent Tutoring Systems (2010–2025) reveals …

2026-05-07 · intelligent-tutoring, benchmark, efficacy-study, higher-ed, k-12

> Conventional LLM safety benchmarks focus on toxic outputs, jailbreaks, and bias. In education, the primary risks are quieter: > "Solving problems correctly and avoiding toxic language does not make …

2026-05-07 · pedagogical-safety, intelligent-tutoring, adaptive-learning, k-12, higher-ed

> Wiggins (1990) proposed AA as a counterbalance to standardised tests: direct examination of "student performance on worthy intellectual tasks." > Authentic assessment (AA) has evolved from workplace…

2026-05-07 · ai-ed-evaluation, ai-education, assessment, formative-assessment, higher-ed

> Hardy & Kim (2026) identify a **cascading proxy** problem in AI-for-education evaluation: > The gap between what LLMs are *capable* of and what actually *benefits learners* — benchmark performance, …

2026-05-07 · llm, benchmark, efficacy-study, bias-mitigation, teacher-role

> Benchmarking vision-language models (VLMs) not on their ability to solve problems, but on their ability to *support learners* — particularly struggling learners and those making errors. Traditional …

2026-05-07 · assessment, multimodal, benchmark, pedagogical-safety, stem-education

> Current AI tutoring systems treat each session as independent. Adaptive systems use real-time knowledge tracing (e.g., [[knowledge-tracing-irt|IRT-based models]]) but rarely retain a longitudinal st…

2026-05-07 · llm, personalized-learning, adaptive-learning, intelligent-tutoring, generative-ai

> The guide adopts a middle way between "techno-fixing" and rejecting AI as an existential threat. It argues that: > A comprehensive educator's guide to integrating Generative AI into multimodal teach…

2026-05-07 · ai-education, higher-ed, generative-ai, multimodal, active-learning

> 1. **Desirable difficulties** — General-purpose AI removes productive struggle; tutoring tools preserve it via graduated hints. 2. **Germane load** — Effective learning requires processing that feel…

2026-05-07 · intelligent-tutoring, llm, generative-ai, personalized-learning, scaffolding