An Adaptive Alignment Method for Learning Path Generation and Learning Objectives Based on the IB-GRPO Large Language Model
Main Article Content
Abstract
Large language models used in personalized education often face mismatches between generated learning paths and teaching objectives, limited adaptive generation ability, and insufficient modeling of heterogeneous learner cognitive profiles. This paper proposes an adaptive alignment method for learning path generation based on the IB-GRPO large language model. First, a multidimensional feature space is constructed by integrating a knowledge graph, learner profiles, and teaching objectives. A knowledge-node importance assessment module dynamically assigns weights to learning content. Second, learners are clustered according to cognitive levels, and a group relative policy optimization algorithm updates path strategies within each group. Third, a teaching-objective constraint function is introduced, and reinforcement learning is used to realize adaptive alignment between generated paths and learning objectives. Finally, a feedback loop dynamically adjusts path-generation strategies according to learning results. Experiments on a dataset of 5,000 learners show that the method achieves a target coverage rate of 90.8% and an ability matching rate of 93.1%. The results demonstrate that the grouping strategy effectively distinguishes learners’ needs and improves personalized path generation.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
L. Elshani, “Personalized learning path generation based on genetic algorithms,” UBT-ETD, 2021, DOI: 10.33107/UBT-ETD.2021.2649.
F. Li and J. Sun, “Personalized learning path generation algorithm based on graph neural networks,” Lecture Notes on Data Engineering and Communications Technologies, pp. 281-291, 2024, DOI: 10.1007/978-3-031-71619-5_24.
D. Hauk and N. Soujon, “How reliable are large language models in analyzing the quality of written lesson plans? A mixed-methods study from a teacher internship program,” Computers and Education: Artificial Intelligence, vol. 10, no. c, Art. no. 100538, 2026, DOI: 10.1016/j.caeai.2025.100538.
Z. He, W. Xia, K. Dong, et al., “Unsupervised learning style classification for learning path generation in online education platforms,” Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, DOI: 10.1145/3534678.3539107.
X. Wei, W. Han, S. Sun, et al., “Educational psychology-empowered personalized learning path generation strategy,” Learning Technologies, IEEE Transactions on, vol. 18, no. 000, pp. 741-756, 2025, DOI: 10.1109/TLT.2025.3590602.
Y. Qu, L. Wang, H. Zhang, et al., “Personalized learning path generation based on neuro-cognitive collaborative filtering,” 2024, DOI: 10.21203/rs.3.rs-4072040/v1.
S. Ying and Y. Fu, “Knowledge graph construction and personalised learning path generation mechanism for online english teaching and learning,” Applied Mathematics and Nonlinear Sciences, vol. 9, no. 1, 2024, DOI: 10.2478/amns-2024-3609.
Y. S. Soekamto, L. C. Limanjaya, Y. K. Purwanto, et al., “From queries to courses: SKYRAG’s revolution in learning path generation via keyword-based document retrieval,” IEEE Access, vol. 13, pp. 21434-21455, 2025, DOI: 10.1109/access.2025.3535618.
R. Zhang, X. Wu, X. Zhang, et al., “An Instructional Optimization Method Based on Bidirectional Transformer and Reinforcement Learning,” IEEE Access, vol. 13, 2025, DOI: 10.1109/ACCESS.2025.3576878.
C. Tong and C. Ren, “Deep knowledge tracing and cognitive load estimation for personalized learning path generation using neural network architecture,” Scientific Reports, vol. 15, no. 1, 2025, DOI: 10.1038/s41598-025-10497-x.