Personalized Learning Path Planning with Goal-Driven Learner State Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914309908463616 |
|---|---|
| author | Lim, Joy Jia Yin He, Ye Yu, Jifan Cong, Xin Zhang-Li, Daniel Liu, Zhiyuan Liu, Huiqin Hou, Lei Li, Juanzi Xu, Bin |
| author_facet | Lim, Joy Jia Yin He, Ye Yu, Jifan Cong, Xin Zhang-Li, Daniel Liu, Zhiyuan Liu, Huiqin Hou, Lei Li, Juanzi Xu, Bin |
| contents | Personalized Learning Path Planning (PLPP) aims to design adaptive learning paths that align with individual goals. While large language models (LLMs) show potential in personalizing learning experiences, existing approaches often lack mechanisms for goal-aligned planning. We introduce Pxplore, a novel framework for PLPP that integrates a reinforcement-based training paradigm and an LLM-driven educational architecture. We design a structured learner state model and an automated reward function that transforms abstract objectives into computable signals. We train the policy combining supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), and deploy it within a real-world learning platform. Extensive experiments validate Pxplore's effectiveness in producing coherent, personalized, and goal-driven learning paths. We release our code and dataset at https://github.com/Pxplore/pxplore-algo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13215 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Personalized Learning Path Planning with Goal-Driven Learner State Modeling Lim, Joy Jia Yin He, Ye Yu, Jifan Cong, Xin Zhang-Li, Daniel Liu, Zhiyuan Liu, Huiqin Hou, Lei Li, Juanzi Xu, Bin Artificial Intelligence Computation and Language Personalized Learning Path Planning (PLPP) aims to design adaptive learning paths that align with individual goals. While large language models (LLMs) show potential in personalizing learning experiences, existing approaches often lack mechanisms for goal-aligned planning. We introduce Pxplore, a novel framework for PLPP that integrates a reinforcement-based training paradigm and an LLM-driven educational architecture. We design a structured learner state model and an automated reward function that transforms abstract objectives into computable signals. We train the policy combining supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), and deploy it within a real-world learning platform. Extensive experiments validate Pxplore's effectiveness in producing coherent, personalized, and goal-driven learning paths. We release our code and dataset at https://github.com/Pxplore/pxplore-algo. |
| title | Personalized Learning Path Planning with Goal-Driven Learner State Modeling |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2510.13215 |