{"type":"link","version":"1.0","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","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/arxiv2508.11408","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2508.11408.png","thumbnail_width":1200,"thumbnail_height":630}