The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911395180707840 |
|---|---|
| author | Liu, Zhengyuan Yin, Stella Xin Tan, Bryan Chen Zhengyu Lee, Roy Ka-Wei Liu, Guimei Goh, Dion Hoe-Lian Wang, Wenya Chen, Nancy F. |
| author_facet | Liu, Zhengyuan Yin, Stella Xin Tan, Bryan Chen Zhengyu Lee, Roy Ka-Wei Liu, Guimei Goh, Dion Hoe-Lian Wang, Wenya Chen, Nancy F. |
| contents | User simulation is important for developing and evaluating human-centered AI, yet current student simulation in educational applications has significant limitations. Existing approaches focus on single learning experiences and do not account for students' gradual knowledge construction and evolving skill sets. Moreover, large language models are optimized to produce direct and accurate responses, making it challenging to represent the incomplete understanding and developmental constraints that characterize real learners. In this paper, we introduce a novel framework for memory-based student simulation that incorporates developmental trajectories through a hierarchical memory mechanism with structured knowledge representation. The framework also integrates metacognitive processes and personality traits to enrich the individual learner profiling, through dynamical consolidation of both cognitive development and personal learning characteristics. In practice, we implement a curriculum-aligned simulator grounded on the Next Generation Science Standards. Experimental results show that our approach can effectively reflect the gradual nature of knowledge development and the characteristic difficulties students face, providing a more accurate representation of learning processes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05903 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation Liu, Zhengyuan Yin, Stella Xin Tan, Bryan Chen Zhengyu Lee, Roy Ka-Wei Liu, Guimei Goh, Dion Hoe-Lian Wang, Wenya Chen, Nancy F. Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction User simulation is important for developing and evaluating human-centered AI, yet current student simulation in educational applications has significant limitations. Existing approaches focus on single learning experiences and do not account for students' gradual knowledge construction and evolving skill sets. Moreover, large language models are optimized to produce direct and accurate responses, making it challenging to represent the incomplete understanding and developmental constraints that characterize real learners. In this paper, we introduce a novel framework for memory-based student simulation that incorporates developmental trajectories through a hierarchical memory mechanism with structured knowledge representation. The framework also integrates metacognitive processes and personality traits to enrich the individual learner profiling, through dynamical consolidation of both cognitive development and personal learning characteristics. In practice, we implement a curriculum-aligned simulator grounded on the Next Generation Science Standards. Experimental results show that our approach can effectively reflect the gradual nature of knowledge development and the characteristic difficulties students face, providing a more accurate representation of learning processes. |
| title | The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation |
| topic | Computers and Society Artificial Intelligence Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.05903 |