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

TL;DR

This paper introduces Customized Curriculum Learning (CCL), a novel training framework for LLMs that adapts difficulty levels based on model capabilities and uses guided prompting to improve mathematical reasoning performance.

Contribution

The paper proposes a new CCL framework with model-adaptive difficulty definition and guided prompting, improving sample efficiency and reasoning accuracy in LLMs.

Findings

CCL outperforms uniform training on five benchmarks

Effective in supervised fine-tuning and reinforcement learning

Enhances sample utilization and model performance

Abstract

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.