Blanchard / Chen / Chi Artificial Intelligence in Education

27th International Conference, AIED 2026, Seoul, South Korea, June 27–July 3, 2026, Proceedings, Part III
Erscheinungsjahr 2026
ISBN: 978-3-032-29760-0
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 658 Seiten

Reihe: Lecture Notes in Computer Science

This six-volume set LNAI constitutes the refereed proceedings of the 27th International Conference on Artificial Intelligence in Education, AIED 2026, held in Seoul, South Korea, during June 27–July 3, 2026.

The 143 full papers and 165 short papers presented in this book were carefully reviewed and selected from 1241 submissions.

• The conference program comprises seven thematic tracks:
  Track 1: Technical Aspects of AIED
  Track 2: Human Aspects of AIED
  Track 3: Societal Aspects of AIED

This year's theme, "From tools to teammates: human-AI synergy for Augmented Learning" , highlights research on human and AI agency, collaborative intelligence, and human & AI co-evolving. 

Zielgruppe

Research

Autoren/Hrsg.

Blanchard, Emmanuel G.

Chen, Guanliang

Chi, Min

Isotani, Seiji

Inhaltsverzeichnis

.- 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.