EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Cognition Graph for Adaptive Learning: Integrating Reasoning Evidence and Reinforcement Learning

Ying Li, Yiming Gai, Xingyu Wang, Leilei Sun, Xuefei Huang

Applied Sciences · 06.04.2026 · 16 (7) · 3580

DOI: 10.3390/app16073580 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 06.04.2026. Verfasst von Ying Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Higher Education Computer Education Research Association, Strategic Research Project on the Training Reform of Excellent Engineers, International Innovation Institute of Beihang University in Hangzhou.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate modeling of learners’ evolving cognitive states is essential for intelligent educational systems, yet many existing knowledge tracing and graph-based approaches rely on static structures or purely sequential representations that inadequately capture dynamic structural changes in learning processes. This study proposes a Learner Cognitive Graph (LCG) framework that integrates dynamic heterogeneous graph modeling, structured behavioral data acquisition, and reinforcement learning-based intervention optimization. A Dynamic Cognition Graph (DCG) is formally defined as a sequence of temporally evolving graph snapshots representing interactions among learners, knowledge concepts, and exercises. A reverse Turing test-based agent with structured prompting is introduced to collect reasoning-oriented behavioral evidence, improving data reliability for cognitive modeling. Temporal message passing, multi-scale memory updating, and self-supervised learning objectives are employed to construct dynamic cognitive representations. Personalized intervention is formulated as a Markov decision process to optimize long-term learning outcomes. Experiments conducted on real-world and simulated educational datasets demonstrate improved knowledge mastery prediction accuracy, cognitive state transition modeling, and intervention efficiency compared with representative baselines. The proposed framework provides a systematic and scalable approach for dynamic cognitive modeling and adaptive educational support.

Förderung

  • National Higher Education Computer Education Research Association
  • Strategic Research Project on the Training Reform of Excellent Engineers
  • International Innovation Institute of Beihang University in Hangzhou
  • the Research Startup Fund of the International Innovation Institute of Beihang University
  • the Teaching Reform Project of the International Innovation Institute of Beihang University

Zitieren

APA

Li, Y., Gai, Y., Wang, X., Sun, L., & Huang, X. (2026). Dynamic Cognition Graph for Adaptive Learning: Integrating Reasoning Evidence and Reinforcement Learning. Applied Sciences, 16(7), 3580. https://doi.org/10.3390/app16073580

Vancouver

Li Y, Gai Y, Wang X, Sun L, Huang X. Dynamic Cognition Graph for Adaptive Learning: Integrating Reasoning Evidence and Reinforcement Learning. Applied Sciences. 2026;16(7):3580. doi:10.3390/app16073580

BibTeX
@article{Li2026,
  author = {Li, Ying and Gai, Yiming and Wang, Xingyu and Sun, Leilei and Huang, Xuefei},
  title = {Dynamic Cognition Graph for Adaptive Learning: Integrating Reasoning Evidence and Reinforcement Learning},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {3580},
  doi = {10.3390/app16073580}
}
Kostenlos starten →