{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/b3b0fd53-5758-4b5f-99d1-5aea627f1dab\" width=\"1280\" height=\"720\" title=\"Thinking Seeds: Restarting On-Policy RL from the Model&#39;s Own Past Reasoning States — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://montaan.com/","thumbnail_url":"https://montaan.com/media/episodes/b3b0fd53-5758-4b5f-99d1-5aea627f1dab/episode.poster.webp","title":"Thinking Seeds: Restarting On-Policy RL from the Model's Own Past Reasoning States","type":"video","version":"1.0","width":1280}