mlsanityData to 14 Oct 2026

Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing

arXiv 2507.11060 ↗First posted 15 Jul 2025cs.AIcited by 4

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

We introduce ExRec, a general framework for personalized exercise recommendation with semantically-grounded knowledge tracing. Our method builds on the observation that existing exercise recommendation approaches simulate student performance via knowledge tracing (KT) but they often overlook two key aspects: (a) the semantic content of questions and (b) the sequential, structured progression of student learning. To address this, our ExRec presents an end-to-end pipeline, from annotating the KCs of questions and learning their semantic representations to training KT models and optimizing several reinforcement learning (RL) methods. Moreover, we improve standard Q-learning-based continuous RL methods via a tailored model-based value estimation (MVE) approach that directly leverages the components of KT model in estimating cumulative knowledge improvement. We validate the effectiveness of our ExRec using various RL methods across four real-world tasks with different educational goals in online math learning. We further show that ExRec generalizes robustly to new, unseen questions and that it produces interpretable student learning trajectories. Together, our findings highlight the promise of KT-guided RL for effective personalization in education.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 45 of its 107 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

45 of 107 references.

References · 45

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  7. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  8. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  9. 2015Deep Knowledge Tracingcited by 332
  10. 2019Soft Actor-Critic for Discrete Action Settingscited by 174
  11. 2020Context-Aware Attentive Knowledge Tracingcited by 174
  12. 2019A Self-Attentive model for Knowledge Tracingcited by 172
33 more
  1. 2016Dynamic Key-Value Memory Networks for Knowledge Tracingcited by 171
  2. 2018Model-Based Value Estimation for Efficient Model-Free Reinforcement Learningcited by 156
  3. 2021Tianshou: a Highly Modularized Deep Reinforcement Learning Librarycited by 143
  4. 2019EKT: Exercise-aware Knowledge Tracing for Student Performance Predictioncited by 109
  5. 2019EdNet: A Large-Scale Hierarchical Dataset in Educationcited by 108
  6. 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solvingcited by 84
  7. 2020Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracingcited by 81
  8. 2022Knowledge Tracing: A Surveycited by 77
  9. 2020Instructions and Guide for Diagnostic Questions: The NeurIPS 2020 Education Challengecited by 64
  10. 2020RKT : Relation-Aware Self-Attention for Knowledge Tracingcited by 62
  11. 2019Knowledge Tracing with Sequential Key-Value Memory Networkscited by 60
  12. 2018Addressing Two Problems in Deep Knowledge Tracing via Prediction-Consistent Regularizationcited by 55
  13. 2022pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Modelscited by 52
  14. 2019Deep-IRT: Make Deep Learning Based Knowledge Tracing Explainable Using Item Response Theorycited by 51
  15. 2023simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracingcited by 47
  16. 2018Knowledge Tracing Machines: Factorization Machines for Knowledge Tracingcited by 42
  17. 2023Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representationscited by 32
  18. 2021Enhancing Knowledge Tracing via Adversarial Trainingcited by 31
  19. 2021A Survey of Knowledge Tracing: Models, Variants, and Applicationscited by 30
  20. 2020qDKT: Question-centric Deep Knowledge Tracingcited by 24
  21. 2023Enhancing Deep Knowledge Tracing with Auxiliary Taskscited by 24
  22. 2019Knowledge Query Network: How Knowledge Interacts with Skillscited by 23
  23. 2022Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracingcited by 23
  24. 2024Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Taskcited by 21
  25. 2023Adaptive and Personalized Exercise Generation for Online Language Learningcited by 19
  26. 2024Towards Robust Knowledge Tracing Models via k-Sparse Attentioncited by 19
  27. 2023Forgetting-aware Linear Bias for Attentive Knowledge Tracingcited by 13
  28. 2024Predictive, scalable and interpretable knowledge tracing on structured domainscited by 13
  29. 2024Automated Generation and Tagging of Knowledge Components from Multiple-Choice Questionscited by 13
  30. 2024Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracingcited by 11
  31. 2022DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracingcited by 9
  32. 2022HiTSKT: A Hierarchical Transformer Model for Session-Aware Knowledge Tracingcited by 8
  33. 2024Large Language Model Augmented Exercise Retrieval for Personalized Language Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Hey Chat, Can You Teach Me? Structuring Socratic Dialogue for Human Learning in the Wildcited by 1
  2. 2026KT4EQG: Personalized Exercise Question Generation via Knowledge Tracingcited by 0
  3. 2026Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistantscited by 0
  4. 2026SRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Taggingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Representation Learning of Auxiliary Concepts for Improved Student Modeling and Exercise Recommendation
  2. 2025Ken Utilization Layer: Hebbian Replay Within a Student's Ken for Adaptive Exercise Recommendation
  3. 2025TutorLLM: Customizing Learning Recommendations with Knowledge Tracing and Retrieval-Augmented Generation
  4. 2025Enhancing Learning Path Recommendation via Multi-task Learning
  5. 2025Personalized Education with Ranking Alignment Recommendation
  6. 2025CLLMRec: LLM-powered Cognitive-Aware Concept Recommendation via Semantic Alignment and Prerequisite Knowledge Distillation
  7. 2026Beyond Static Question Banks: Dynamic Knowledge Expansion via LLM-Automated Graph Construction and Adaptive Generation
  8. 2024A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documents