grpo
LongStraw Makes Million-Token RL Training Possible on 8 GPUs - But Its Code Doesn't Run Yet News
A new systems paper called LongStraw shows reinforcement-learning post-training can execute on prompts beyond 2 million tokens on a fixed 8-GPU budget by scoring the shared prompt once without gradients and backpropagating only through the short generated response, though the authors call this proof of execution capacity rather than full training correctness, and the public code is not yet runnable.
Group Relative Policy Optimization (GRPO) Lesson
GRPO is the reinforcement learning method behind most modern reasoning models: instead of training a separate 'critic' network to judge answers, it samples a whole group of answers to each question and scores each one by how it compares to the group's average.
Three Popular Ways to Train Reasoning AIs Turn Out to Be One Formula News
A new proof shows that three widely used reinforcement-learning recipes for training reasoning models - GRPO, Dr. GRPO, and DAPO - are all just different operations on a single number, the spread of rewards within a group of sampled answers.
prime-rl Tool
Open-source RL post-training stack that splits rollout generation and gradient updates across GPUs, used in this week's widely discussed $500 fine-tune that beat five frontier configurations on a catalog-review workflow. Practical for teams that already have an automatically scored task and want to train a specialist rather than pay per call for a frontier model.