Research on Personalized Learning Systems Driven by Multi-Agent Collaboration

DOI

10.2991/978-94-6239-733-0_7How to use a DOI?

Keywords

Profiling; Multi-Agent Collaboration; Socratic Dialogue; Personalized Learning Path; Cognitive Advancement

Abstract

Multi-agent collaboration provides a scalable solution for personalized learning path generation, tackling the long-standing challenge of adaptive instruction. Although previous research has improved agent functions and learner modeling, the integration of Socratic dialogue mechanisms remains underexplored. To address this gap, this paper presents a framework that unifies learner profiling, multi-agent collaboration, and dynamic path generation. A dynamic learner state vector is constructed to represent knowledge mastery, cognitive depth, and engagement. Four specialized agents—cognitive diagnosis, question generation, metacognitive regulation, and path evolution—work together to guide instructional decisions. Central to the framework is a Socratic dialogue engine that leads learners through a three-tiered question chain (clarification, probing, and refutation) to stimulate cognitive conflict and foster higher-order thinking. The proposed approach is both theoretically grounded and practically implementable. Its feasibility is demonstrated through algorithmic specifications and simulated learner trajectories, showing clear potential for real-world deployment in intelligent tutoring systems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yiying Ye
AU  - Yuhui Jing
PY  - 2026
DA  - 2026/07/17
TI  - Research on Personalized Learning Systems Driven by Multi-Agent Collaboration
BT  - Proceedings of the 6th International Conference on Internet, Education and Information Technology (IEIT 2026)
PB  - Atlantis Press
SP  - 48
EP  - 53
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-733-0_7
DO  - 10.2991/978-94-6239-733-0_7
ID  - Ye2026
ER  -