Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.27695 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914430063738880 |
|---|---|
| author | Silva, Ricardo Pedro Querido Andrade Bouarour, Nassim Fettache, Dina Boussouar, Sarab Ibrahim, Noha Amer-Yahia, Sihem |
| author_facet | Silva, Ricardo Pedro Querido Andrade Bouarour, Nassim Fettache, Dina Boussouar, Sarab Ibrahim, Noha Amer-Yahia, Sihem |
| contents | Quiz design is a tedious process that teachers undertake to evaluate the acquisition of knowledge by students. Our goal in this paper is to automate quiz composition from a set of multiple choice questions (MCQs). We formalize a generic sequential decision-making problem with the goal of training an agent to compose a quiz that meets the desired topic coverage and difficulty levels. We investigate DQN, SARSA and A2C/A3C, three reinforcement learning solutions to solve our problem. We run extensive experiments on synthetic and real datasets that study the ability of RL to land on the best quiz. Our results reveal subtle differences in agent behavior and in transfer learning with different data distributions and teacher goals. This was supported by our user study, paving the way for automating various teachers' pedagogical goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27695 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimizing Coverage and Difficulty in Reinforcement Learning for Quiz Composition Silva, Ricardo Pedro Querido Andrade Bouarour, Nassim Fettache, Dina Boussouar, Sarab Ibrahim, Noha Amer-Yahia, Sihem Machine Learning Quiz design is a tedious process that teachers undertake to evaluate the acquisition of knowledge by students. Our goal in this paper is to automate quiz composition from a set of multiple choice questions (MCQs). We formalize a generic sequential decision-making problem with the goal of training an agent to compose a quiz that meets the desired topic coverage and difficulty levels. We investigate DQN, SARSA and A2C/A3C, three reinforcement learning solutions to solve our problem. We run extensive experiments on synthetic and real datasets that study the ability of RL to land on the best quiz. Our results reveal subtle differences in agent behavior and in transfer learning with different data distributions and teacher goals. This was supported by our user study, paving the way for automating various teachers' pedagogical goals. |
| title | Optimizing Coverage and Difficulty in Reinforcement Learning for Quiz Composition |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.27695 |