Artificial Intelligence in Education

.- Agnoagentia: The Illusion of Agency in AI-Assisted Learning.
.- Do Instructional Behaviors Generalize Across Disciplines? An Empirical Study with Fine-Tuned Multimodal LLMs.
.- From Black-Box Generation to Pedagogically Controllable Creation: A Text-to-Image Interactive System in Design Education.
.- Scaffolding-First Constraint Design for LLM Tutors in Data-Science Problem Solving.
.- Representation Learning to Study Temporal Dynamics in Tutorial Scaffolding.
.- Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design.
.- Multi-Label Collaborative Dialogue Act Recognition for Adaptive Team Training Environments.
.- Circuit Complexity of Hierarchical Knowledge Tracing.
.- Beyond the Gold Standard: Reliability Estimation of Human and GenAI Scoring.
.- CODE-GEN: A RAG-Based Agentic AI System for Multiple-Choice Question Generation.
.- Content-Grounded Learning Behavior Analysis for Contextualized Feedback.
.- Evaluating a Data-Driven Redesign Process for Intelligent Tutoring Systems.
.- Time-window ONA: Model the impact of utterances in Ordered Network Analysis.
.- On Generating and Validating Erroneous Examples in CS1 using LLMs.
.- Contrastive Network-based Similarity for Zero-Shot Automatic Scoring of Very Short Handwritten Answers.
.- MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning.
.- Peer and Tutor in One: A Productive Failure-Based Architecture for Multi-Role Conversational Agents in
Physics Learning.
.- EduArt-Bench: A Benchmark and Lightweight Scoring Calibration for K-12 Art Education.
.- Conceptualization of Thinking Activities-specific Metacognitive Knowledge Ontology.
.- Mix and Match: Context Pairing for Scalable Topic-Controlled Educational Summarisation.
.- Study Program Curriculum Development with AI.
.- Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs.
.- Decoding Latent Reasoning: Mechanistic Interpretability ofChain of Continuous Thought with Sparse Autoencoders.
.- Personalizing Mathematical Game-based Learning for Children: A Preliminary Study.
.- A Hybrid Human-AI Content Generation Framework for Safe and Personalized Dialogic Learning with Children.
.- Likelihood-Based Diagnosis with Generative Models:Confidence-Aware Measurement from Student Writing.
.- Delegating Educational Tasks to Large Language Models: A Systematic Analysis of Evaluation Approaches.
.- An ORID-Structured GenAI Reading Companion Integrating Structured Book Chat and Virtual Labs for Science Reading.
.- Large Language Models for Automated Bloom's Taxonomy Classification in Computer Science Assessment.
.- A Framework for Human-AI Q-Matrix Refinement: A NeuralCDM Evaluation.
.- MCQ Difficulty Prediction through Modeling Learner Heterogeneity using Data-Driven Cognitive Profiling.
.- Can Large Language Models Learn to Grade Like Teachers? A Few-Shot Study on Open-Ended Assessment.
.- ArguAgent: AI-Supported Real-Time Grouping for Productive Argumentation in STEM Classrooms.
.- Minimizing Data Exposure in Higher Education LLM Applications: Evaluating the Model Context Protocol (MCP) for Preserving Privacy in Academic Advising.
.- Re-imagine Knowledge Tracing with Student Agency in a Generative AI Language Tutor.
.- From Predictive Models to Actionable Recommendations: A Survey of Counterfactual Approaches in Student Dropout.
.- Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings.
.- Confidence-Aware Automated Assessment of Student-Drawn Scientific Models.
.- Exploring Question Isomorphism through Different Numerical and Computational Representations.
.- A Generator-Aligner Pipeline for LLM-Based Situational Judgment Test Generation.
.- When Can We Trust AI Coding of Student-Generated Text? A Committee-Based Approach to Diagnosing Agreement and Uncertainty at Scale.
.- From Rule-Based to LLM-Based Agents: A Calibrated Simulation Framework for Classroom Social Networks.
.- Making Advanced Temporal Visualizations Accessible to Educators Using Generative AI.
.- FairDetect: Training-Time Fairness for AI-Generated Text Detection via Perplexity-Adaptive Focal Loss.
.- Reliability as a Teammate: Budgeted Verifier-in-the-Loop (BVIL) Policies for Reliable LLM Tutoring Actions.
.- Estimating Learners' Skill Acquisition Without Temporal Information.
.- Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?.
.- From Exploration to Creation: How Teachers Orchestrate AI-Supported Learning in History Classrooms.
.- Explaining, Solving, or Generating? Functional Differences in Students' AI Use in a University Database Course.
.- Leveraging Human-AI Collaboration for a Passage-Based Question Authoring Tool.
.- Automating Supportive Psychological Processes: How Source Attribution Shapes Perceived Empathy, Working Alliance, and Acceptability of a Supportive Conversa-tional Agent.
.- Tailoring AI-Driven Reading Scaffolds to the Distinct Needs of Neurodiverse Learners.
.- Should AI Ask First? Investigating the Effects of Proactive vs Reactive AI Mentoring in Self-Directed Learning.
.- Uncertain AI - Better AI? Effects of Uncertainty Indicators in Collaborative Learning with a Human Peer or an Artificial Intelligence.
.- Using LLMs to score mathematics lessons for instructional quality with the UTOP.
.- Making AI Planning Visible: Narrative-Centered Goal-Directed AI Reasoning to Foster AI Literacy.
.- A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics.
.- Teachers' Perspectives on Decision-Making in AI-Supported Classrooms: A Cross-Cultural Study of Germany and Japan.
.- AI Partners that Support Productive Uncertainty within "Jigsaw" Activities during Small Group Collaborative Learning in Classrooms.
.- Impact of Multimodal and Conversational AI on Learning Outcomes and Experience.
.- From Examples to Rules? Exploring Inductive Reverse Engineering and Deductive Few-Shot Coding via LLMs for Qualitative Data Analysis.