2026
Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
ICLR 2026poster
We aim to improve the reasoning capabilities of language models via reinforcement learning with verifiable rewards (RLVR). Recent RLVR post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies suggest that using RLVR alone to…