Agentic RL 2: RL for LLMs
RL Methods for LLM PostTraining (vanilla-ppo, RLHF-PPO, DPO, RLVR, DeepSeek-Math-GRPO)
Post-Training
Agentic RL 3: From Tokens to Trajectories, Long-Horizon Reinforcement Learning
What is after GRPO? Advanced long-horizon agentic reinforcement learning. (DAPO, GSPO, SAO, FlashREINFORCE, more advanced training recipes.)
Slime101: Slime Core Training Pipeline
Core Slime training pipeline analysis. (Ray, Megatron, SGLang)
Frontier Post Training Pipelines
Post-training analysis & summaries from frontier base model tech reports (continuously updated).