{"type":"link","version":"1.0","title":"Iterative self-play grows a tool-use dataset from a handful of demonstrations by repeatedly fine-tuning, sampling, filtering, and re-adding","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/iterative-self-play-bootstraps-tool-use-from-few-demonstrations","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}