Agentic RL on Frontier LLM Notes

Agentic RL on Frontier LLM Notes https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/ Recent content in Agentic RL on Frontier LLM Notes Hugo zh-cn Mon, 02 Nov 2026 20:39:37 +0800 Agentic RL 2: RL for LLMs https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/rl-for-llms/ Mon, 02 Nov 2026 20:39:37 +0800 https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/rl-for-llms/ RL Methods for LLM PostTraining (vanilla-ppo, RLHF-PPO, DPO, RLVR, DeepSeek-Math-GRPO) Agentic RL 3: From Tokens to Trajectories, Long-Horizon Reinforcement Learning https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/from-tokens-to-trajectories/ Mon, 19 Oct 2026 22:46:32 +0800 https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/from-tokens-to-trajectories/ What is after GRPO? Advanced long-horizon agentic reinforcement learning. (DAPO, GSPO, SAO, FlashREINFORCE, more advanced training recipes.) Agentic RL 1: From Policy Gradient to PPO https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/from-policy-gradient-to-ppo/ Mon, 12 Oct 2026 17:27:41 +0800 https://xiyuanyang-code.github.io/llm/posts/post-training/agentic-rl/from-policy-gradient-to-ppo/ From RL Basis to Policy Gradient (reward-to-go, advantage estimations), REINFORCE, Actor-Critic, PPO (Importance Sampling and Clipping)