Blanchard / Chen / Chi Artificial Intelligence in Education

27th International Conference, AIED 2026, Seoul, South Korea, June 27–July 3, 2026, Proceedings, Part I
Erscheinungsjahr 2026
ISBN: 978-3-032-29744-0
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 649 Seiten

Reihe: 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

.- Evidence–Decision–Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents.
.- DrawSim-PD: Simulating Student Science Drawings to Support NGSS-Aligned Teacher Diagnostic Reasoning.
.- Enhancing Intelligent Tutoring Systems with Instruction-Tuned LLMs: Automated Assessment of Student
Code Comprehension.
.- Automatically Inferring Teachers' Geometric Content Knowledge: A Skills Based Approach.
.- Personalized AI Practice Replicates Learning Rate Regularity at Scale.
.- Benchmarking Scientific Formula Vocalization in Large Speech Language Models Toward Accessible Learning.
.- From Untamed Black Box to Interpretable PedagogicalOrchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring.
.- Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math.
.- Prompt Optimization with Verifiable Rewards for Synthetic Essay Generation.
.- Generating Personalized Programming Exercises via Cognitive State Graphs and ZPD-Driven Prompting.
.- Short, Long, or Affective: Evaluating LLM-Generated Feedback Styles for Student Learning.
.- Developing and Evaluating a Large Language Model–Based Tool for Qualitative Analysis of Teacher Interviews.
.- An Explainable AI Assistant for Introductory Programming Education: Improving Feedback Reliability with Instructor-AI Collaboration.
.- Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards.
.- Beyond Show and Tell: Explainable AI-Supported Feedback for Developing Data Visualization Sense-Making Skills.
.- A Multi-Agent Approach to Validate and Refine LLM-Generated Personalized Math Problems.
.- Gaze to Insight: A Scalable AI Approach for Detecting Gaze Behaviours in Face-to-Face Collaborative Learning.
.- When AI Meets Early childhood education: Large Language Models as Assessment Teammates in Chinese Preschools.
.- From Slides to Exams: A Multi-Agent Human-AI System for Collaborative Assessment Design.
.- I-VIP: A LLM-Driven Multi-Agent System for Professional Development of Mathematics Teachers.
.- A Neuro-Symbolic Approach to Extracurricular Activity Recommendation Based on Cognitive Profiling.
.- From Problem Solving to Pedagogical Feedback: Student-Centric Tree-of-Thought Reasoning for Student Error Attribution.
.- ANVIL: Analogies and Videos for Lecturers.
.- Process-Integrated IRT: Enhancing Ability Estimation in Computer-based Programming Assessments through Response Process Data.
.- New Intent Discovery for Educational Dialogue Texts via Semantic-Aware Data Augmentation.
.- When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment.
.- REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour.
.- The TME Framework: Multimodal Learner Modeling for Active Listening Skills in Collaborative Problem Solving.
.- An Item Response Theory Model for Addressing Halo Effects in Performance Assessment.
.- LLM-based Virtual Standardized Patients with Response Excessiveness Suppression via Direct Preference Optimization for Medical Interview Examinations.
.- PSC: Personalized Sentence-level Pronunciation Coaching Framework for Thai EFL Learners.
.- Building Evidence-Linked Curriculum Knowledge Graphs for Academic Pathway Planning.
.- Misconception Acquisition Dynamics in Large Language Models.
.- Beyond Next-Response Prediction: Evaluating Knowledge State Transition Consistency in Deep Learning Based Knowledge Tracing Models.
.- Grounding Programming Chatbot in Computational Thinking:Design and Evaluation of MazeMate.
.- SciEval: A Benchmark for Automatic Evaluation of K–12 Science Instructional Materials.
.- Has Automated Essay Scoring Reached Sufficient Accuracy?Deriving Achievable QWK Ceilings from Classical Test Theory.
.- Automated Multimodal Transcription for Belonging-centered Classroom Interaction Analysis: Opportunities and Challenges.
.- Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors.
.- SLOW: Strategic Logical-inference Open Workspace for Cognitive Adaptation in AI Tutoring.
.- From Learning Resources to Competencies: LLM-Based Tagging with Evidence and Graph Constraints.
.- Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models.