Intelligent and Adaptive Learning Systems across Educational Contexts

Aim and Scope

Now in its seventh consecutive edition, this invited session focuses on intelligent and adaptive learning systems operating across diverse educational contexts, from higher education and K-12 to lifelong, workplace, and informal learning. The rapid spread of large language models (LLMs) and agentic AI has moved such systems beyond the Learning Management System (LMS) into conversational tutors, AI teaching assistants, embodied agents, social robots, and immersive environments. These advances create new opportunities for personalization and scalable feedback. They also raise pressing questions about learning validity, assessment integrity, learner agency, privacy, fairness, and accountability. These questions are made more urgent as regulations such as the EU AI Act classify many educational AI applications as high-risk.

This session brings together researchers and practitioners to discuss the design, evaluation, and responsible deployment of intelligent learning systems. We particularly welcome empirically grounded studies that capture and analyze learner interaction data using data mining, deep learning, natural language processing, and multimodal learning analytics, and that report evidence of effects on learning processes and outcomes. Contributions that bridge technical innovation with pedagogical and human-centered perspectives, including learner modeling, affective and metacognitive support, human-AI collaboration in teaching, and trustworthy AI, are especially encouraged.

Topics of Interest

Topics of interest include, but are not limited to:

• Generative and Agentic AI for Learning
  • LLM-based tutors and teaching assistants
  • Agentic and multi-agent systems for instructional support
  • Automatic feedback and question generation
  • AI literacy and prompt literacy
• Adaptive Learning, Learner Modeling, and Analytics
  • Adaptive support, learner modeling, and knowledge tracing
  • Modeling of motivation, metacognition, and affect
  • Learning analytics, multimodal learning analytics, and educational data mining
  • Recommender systems for education
• Assessment and Evidence
  • AI-assisted assessment and automated scoring
  • Academic integrity in the generative AI era
  • Evaluation methodologies and evidence-based education
• Trustworthy and Responsible AI in Education
  • Privacy, security, and governance of educational data
  • Bias, fairness, and explainability
  • Human oversight and regulatory compliance (e.g., EU AI Act)
• Embodied, Immersive, and Interactive Learning
  • AR/VR/XR in education
  • Social robots and embodied conversational agents
  • Gamification and embodied learning for wellbeing
• Infrastructure and Practice
  • LMS and interoperability standards (e.g., LTI, xAPI)
  • Curriculum and instructional design
  • Practices in specific contexts (e.g., language learning, STEAM, data science and AI education, disaster prevention)

Submission

KES2027 Invited Sessions Submission

Contact

Chair

Prof. Dr. Hiroshi Ueda (Hosei University, Japan)

Co-Chair

Dr. Mohammad Nehal Hasnine (Arizona State University, USA)

Prof. Dr. Hiroya Suno (Hosei University, Japan)

Assoc. Prof. Dr. Qian Wu (Hosei University, Japan)

Assoc. Prof. Dr. Hisashi Hatakeyama (Institute of Science Tokyo, Japan)

Main Contributing Research Centres

Research Center for Computing and Multimedia Studies, Hosei University, Japan

Learning Engineering Institute, Arizona State University, USA

Email

media-kesis2027@ml.hosei.ac.jp