Research
I study AI-native learning systems: how AI reshapes teaching, learning, and educational relationships.
Explore our team’s research, projects and publications.
Research Framework
Organized around four interconnected layers (click to jump):
1. Educational Philosophy & Ethics
How does AI reshape the nature of learning, agency, and education? Examines how students, teachers, AI systems, and environments co-constitute learning processes. Focuses on human, pedagogical, and epistemic agency; distributed cognition; ethical risks of over-optimization.
2. AI-Native Learning Infrastructure
How can learning systems be designed as integrated, AI-native environments? Focuses on multi-agent systems, classroom orchestration platforms, collaborative environments, AI agent creation systems that support teaching, learning, and real-time intervention.
3. Learning Analytics & Interpretation
How can classroom processes be made visible and interpretable? Integrates classroom discourse, video/audio data, interaction logs, teacher planning data, student assessment data. Goal: not only prediction, but interpretation — supporting teacher reflection and instructional decision-making.
4. Learning & Teaching Outcomes
What impact do AI-supported systems have? Examines student development (AI literacy, computational thinking, problem solving, epistemic agency) and teacher development (agency, design capability, professional growth), alongside changes in classroom practices.
Research Themes
Six interconnected themes. Click a node to jump:
Human–AI Co-Configuration in Education
How are educational processes reconfigured when humans and AI jointly constitute learning systems? This theme brings together human–AI assemblages, teacher–AI co-creation, and student–AI co-creation — where students learn through designing, testing, and refining AI agents. Focuses on distributed agency, pedagogical agency, and epistemic agency.
Selected Work
· Teachers' Behavior in Building Agents Based on Hierarchical Clustering and Thematic Analysis (AERA 2026)
· Empowering Teachers as Creators of Pedagogical Agents: An Integrated Perspective of Constructionism, ICAP, and TPACK (AERA 2026)
· An Activity-Theoretical Approach to Teacher Professional Development in Pedagogical AI Agent Design (ISLS, ICLS 2026)
· Modeling AI-TPACK in Practice: Insights from Teachers' Multi-Agent Workflow Design (ISLS, ICLS 2026)
· Computational Thinking Development in AI Agent Creation: A Mixed-Methods Study (AIED 2026)
Multi-Agent Learning Systems
How can coordinated AI agents support teaching and learning processes? This work treats multi-agent systems as educational infrastructure, not isolated tools. Explores agent orchestration, teacher–student–AI coordination, and system-level intelligence in classrooms.
Selected Work
· MIRACLE: Multi-Agent Intelligent Regulation to Advance Collaborative Learning Environment (ISLS, CSCL 2026) — Best Short Paper Award
· Hierarchical Multi-Agent System for Instructional Design in Music Knowledge Building (ISLS, CSCL 2026)
· A Multi-Agent System (MAS)-Based Tool to Support Novice Teachers in Knowledge Building Pedagogy (ISLS, CSCL 2025)
Collaborative Learning & Knowledge Building
How can AI support collective cognition and socially shared regulation? Focuses on collaborative environments such as CocoNote, examining group cognition, knowledge building processes, and socially shared regulation of learning.
Selected Work
· CocoNote Supported Project-Based Learning Environment: Perspectives of Construction and Collaboration (ISLS, CSCL 2024)
· CocoNote: Agents-aided Collaborative Learning Environment Enhances Socially Shared Regulation (ISLS, CSCL 2025) 🏆
· MIRACLE: Multi-Agent Intelligent Regulation to Advance Collaborative Learning Environment (ISLS, CSCL 2026) — Best Short Paper Award
Multimodal Learning Analytics
How can multimodal data support interpretation of classroom processes? Develops approaches to classroom discourse analysis, integration of multimodal data streams (audio, video, interaction logs, assessment data), and teacher-facing analytics for reflection and decision-making.
Selected Work
· Teachers' Behavior in Building Agents Based on Hierarchical Clustering and Thematic Analysis (AERA 2026)
· Modeling AI-TPACK in Practice: Insights from Teachers' Multi-Agent Workflow Design (ISLS, ICLS 2026)
Ongoing
· Integrating audio, video, interaction logs, and assessment data
· Supporting teacher reflection through interpretable analytics
Student Development in AI-Mediated Learning
How does participation in AI-mediated environments shape student development? Examines how iterative cycles of design, testing, debugging, and refinement support computational thinking, self-efficacy, and epistemic agency. Also investigates variation across learners, including non-linear development patterns.
Selected Work
· Computational Thinking Development in AI Agent Creation: A Mixed-Methods Study (AIED 2026)
Adaptive & Ethical Human–AI Learning Design
How can AI support learning without constraining agency? Extends beyond traditional adaptive learning by focusing on epistemic agency, human–AI interaction design, and ethical implications.
Ongoing
· Designing systems that expand, rather than narrow, learner possibilities
· Balancing personalization with openness
· Understanding how AI reshapes learning trajectories
Selected Publications
Sun, Y., Xin, H., Niu, Q., Li, S., Huang, L., & Chen, G. (2026, June). Computational thinking development in AI agent creation: A mixed-methods study [Short paper]. Proceedings of the 2026 International Conference on Artificial Intelligence in Education (AIED), Seoul, Republic of Korea.
Xin, H., Niu, Q., Li, S., Sun, Y., Chai, C., Huang, L., & Chen, G. (2026, June). An activity-theoretical approach to teacher professional development in pedagogical AI agent design [Long paper]. Proceedings of the 2026 ISLS Annual Meeting, Irvine, CA.
Sun, Y., Xin, H., Li, S., Niu, Q., Chai, C., Huang, L., & Chen, G. (2026, June). Modeling AI-TPACK in practice: Insights from teachers' multi-agent workflow design [Short paper]. Proceedings of the 2026 ISLS Annual Meeting, Irvine, CA.
Li, S., Xin, H., Sun, Y., Niu, Q., Huang, L., Chen, G., Zhang, Y., & Chai, C. S. (2026). MIRACLE: Multi-agent intelligent regulation to advance collaborative learning environment. In C. Rosé, G. Gweon, C. Asterhan, & A. Keune (Eds.), Proceedings of the 19th International Conference on Computer-Supported Collaborative Learning — CSCL 2026 (pp. 524–528). International Society of the Learning Sciences. Best Short Paper Award — CSCL 2026.Read paper
Zhang, M., Zhu, M., Xin, H., & Zhang, Y. (2026, June). Hierarchical multi-agent system for instructional design in music knowledge building [Poster]. Proceedings of the 2026 ISLS Annual Meeting, Irvine, CA.
Xin, H., Yu, Y., Li, S., Niu, Q., Gao, L., Huang, L., & Chai, C. (2026, April). Teachers' behavior in building agents based on hierarchical clustering and thematic analysis [Roundtable]. 2026 AERA Annual Meeting, Los Angeles, CA.
Li, S., Xin, H., Yu, Y., Niu, Q., Gao, L., Huang, L., & Chai, C. (2026, April). Empowering teachers as creators of pedagogical agents: An integrated perspective of constructionism, ICAP, and TPACK [Poster]. 2026 AERA Annual Meeting, Los Angeles, CA.
Xin, H., Li, S., Huang, L., Yip, V. W. Y., Niu, Q., Chen, X., & Liu, J. (2025). CocoNote: Agents-aided collaborative learning environment enhances socially shared regulation [Short paper]. Proceedings of CSCL 2025. 🏆 Outstanding Short Paper Award
Xin, H., Lan, L., Niu, Q., Hu, Z., & Zhang, Y. (2025). A multi-agent system (MAS)-based tool to support novice teachers in knowledge building pedagogy. Proceedings of CSCL 2025.
Xin, H., Niu, Q., Lan, L., Xiao, Z., & Wu, F. (2024). CocoNote supported project-based learning environment: Perspectives of construction and collaboration [Poster]. Proceedings of CSCL 2024.
Zhong, X., Xin, H., Li, W., Zhan, Z., & Cheng, M. (2024). The design and application of RAG-based conversational agents for collaborative problem solving. Proceedings of the 2024 9th International Conference on Distance Education and Learning.