Long-Horizon on Frontier LLM Notes

Long-Horizon on Frontier LLM Notes https://xiyuanyang-code.github.io/llm/tags/long-horizon/ Recent content in Long-Horizon on Frontier LLM Notes Hugo zh-cn Mon, 19 Oct 2026 22:46:32 +0800 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.)