GenAL: Generative Agent for Adaptive Learning

GenAL: генеративный агент для адаптивного обучения
Junyu Lu, Qi Liu, Haotian Zhang, Rui Lv, Weibo Gao, Linbo Zhu
2025-04-11

adaptive learninggenerative agentslarge language modelslearner profilinglearning path recommendation
Adaptive learning, also known as adaptive teaching, relies on learning path recommendations that sequentially suggest personalized learning items (such as lectures and exercises) to meet the unique needs of each learner. Despite the extensive research in this field, previous approaches have primarily modeled the interaction sequences between learners and items using simple indexing, leading to three issues: (1) The utilization of information from both learners and items is not sufficient. For instance, these models are unable to leverage the semantic information contained within the textual content of the items. (2) Models need to be retrained on different datasets separately, which makes it difficult to adapt to the continuously expanding item pool in online educational scenarios. (3) The existing recommendation paradigm based on trained reinforcement learning frameworks, suffers from unstable recommendation performance in sparse learning logs. To address these challenges, we propose a generalized Generative Agent for Adaptive Learning (GenAL), which integrates educational tools with LLMs' semantic understanding to enable effective and generalizable learning path recommendations across diverse data distributions. Specifically, our framework consists of two components: the Global Thinking Agent, which updates the learner profile and reflects on recommendation outcomes based on the learner's historical learning records. The other is the Local Teaching Agent, which recommends items using educational prior knowledge. Leveraging the LLM's robust semantic understanding, our framework does not rely on item indexing but instead extracts relevant information from the textual content. We evaluated our approach on three real-world datasets, and the experimental results demonstrate that our GenAL not only consistently outperforms all baselines but also exhibits strong generalization ability.
1
By avoiding item indexing, GenAL can adapt to continuously expanding item pools without separate retraining for different datasets.
2
Experiments on three real-world datasets show that GenAL consistently outperforms all baselines and demonstrates strong generalization ability.
3
GenAL integrates educational tools with large language models to generate personalized, generalizable learning paths across diverse data distributions.
4
The Global Thinking Agent updates learner profiles and reflects on recommendation outcomes using historical learning records.
5
The Local Teaching Agent recommends learning items using educational prior knowledge and semantic information from item text rather than item indexing.

adaptive learning path recommendation involving learners and educational items

personalized, semantically informed, and generalizable learning path recommendation across diverse data distributions, including learner-profile updating and recommendation adaptation

Publication Details
Publication Date
2025-04-11
Journal
Publisher
ISSN
Cited by
25
Access Type
Author Information
Authors
Junyu Lu
Qi Liu
Haotian Zhang
Rui Lv
Weibo Gao
Linbo Zhu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%