1
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
基于分布感知的主动轨迹塑造方法，显著加速LLM强化学习训练，已被ICML 2026接收。
arXiv:2605.30859v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rol…