1
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
提出在线验证提示选择方法，大幅提升大推理模型RL训练效率
arXiv:2603.25184v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in…