Notes on agentic LLMs, reinforcement learning, and model training.https://www.agillm.io/https://www.agillm.io/blog/hello-agillm/https://www.agillm.io/blog/hello-agillm/What this site is for, and what I plan to write about.Sun, 06 Sep 2026 00:00:00 GMThttps://www.agillm.io/blog/qwen3-video-grpo-training/https://www.agillm.io/blog/qwen3-video-grpo-training/An interactive visualization of the Qwen3-VL GRPO training pipeline.Sun, 06 Sep 2026 00:00:00 GMThttps://www.agillm.io/blog/qwen3-video-training/https://www.agillm.io/blog/qwen3-video-training/An interactive visualization of the Qwen3-VL supervised fine-tuning pipeline.Sun, 06 Sep 2026 00:00:00 GMT