{"type": "article", "title": "R$^2$PO: Decoupling Rollout and Inference Policies for LLM Reasoning", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/r-2-po-decoupling-rollout-and-inference-policies-for-llm-reasoning", "original_source": "https://www.machinebrief.com/news/rdollar2dollarpo-decoupling-rollout-and-inference-policies-f-t4ka", "published": "2026-07-07T04:00:00+00:00", "accessed": "2026-07-11", "id": "r-2-po-decoupling-rollout-and-inference-policies-for-llm-reasoning"}