{"type":"link","version":"1.0","title":"A model can generate its own search reward by self-scoring step correctness and measuring answer agreement across samples","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/self-evaluation-and-state-confidence-as-intrinsic-search-reward","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}