Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations, we propose Customized Curriculum Learning (CCL), a novel framework with two key innovations. First, we introduce model-adaptive difficulty definition that customizes curriculum datasets based on each model's individual capabilities rather than using predefined difficulty metrics. Second, we develop "Guided Prompting," which dynamically reduces sample difficulty through strategic hints, enabling effective utilization of challenging samples that would otherwise degrade performance. Comprehensive experiments on supervised fine-tuning and reinforcement learning demonstrate that CCL significantly outperforms uniform training approaches across five mathematical reasoning benchmarks, confirming its effectiveness across both paradigms in enhancing sample utilization and model performance.

@article{wu2025_2506.04065,
  title={ Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning },
  author={ Muling Wu and Qi Qian and Wenhao Liu and Xiaohua Wang and Zisu Huang and Di Liang and LI Miao and Shihan Dou and Changze Lv and Zhenghua Wang and Zhibo Xu and Lina Chen and Tianlong Li and Xiaoqing Zheng and Xuanjing Huang },
  journal={arXiv preprint arXiv:2506.04065},
  year={ 2025 }
}