{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/bad1353e-ba65-4b38-8056-32ac66e61e07\" width=\"1280\" height=\"720\" title=\"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization — 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://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/bad1353e-ba65-4b38-8056-32ac66e61e07/episode.poster.webp","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","type":"video","version":"1.0","width":1280}