{"type":"link","version":"1.0","title":"Agents left to choose post-training methods converge on SFT and rarely attempt RL","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/idea-sft-dominates-agent-chosen-post-training-methods","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}