Agentic RL 2: RL for LLMs
RL Methods for LLM PostTraining (vanilla-ppo, RLHF-PPO, DPO, RLVR, DeepSeek-Math-GRPO)
Rl
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.)
MidTraining Overview
Mid-training paper list & tech reports. (Continual pretraining, retention, RL scaling)
Agentic RL 1: From Policy Gradient to PPO
From RL Basis to Policy Gradient (reward-to-go, advantage estimations), REINFORCE, Actor-Critic, PPO (Importance Sampling and Clipping)
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).