Tag
Explains three uses of distillation in frontier model post-training pipelines: compressing large models into small ones, merging RL experts, and self-teaching. Includes a write-up detailing which models use each method.
Introduces Pedagogical RL, a method that leverages privileged information to guide the sampling of successful trajectories for LLM reasoning, achieving up to 40% relative gains over GRPO and on-policy distillation.
Introduces pedagogical RL, a paradigm where privileged self-teachers are trained to generate correct and easy-to-follow rollouts, showing it is a relatively easy RL problem.