{"type":"link","version":"1.0","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood","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/arxiv2604.12736","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2604.12736.png","thumbnail_width":1200,"thumbnail_height":630}