Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning

Understand

We aim to improve the reasoning capabilities of language models via reinforcement learning (RL).

• Recent RL post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks.
• However, prior studies suggest that using RL alone to improve reasoning on inherently difficult tasks is less effective.
• Here, we draw inspiration from curriculum learning and propose to schedule tasks from easy to hard (E2H), allowing LLMs to build reasoning skills gradually.