{"type":"link","version":"1.0","title":"Treating SFT-to-RL data split ratio as a hyperparameter substantially outperforms naive phase-boundary allocation","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/sft-rl-data-ratio-determines-agent-training-ceiling","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}