SOURCE-LINKED INTELLIGENCE

From Rollouts to Recipes: Self-Contained Post-Training for LLMs

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Post-training large language models usually applies a single training recipe to all samples, even though the model's own rollouts reveal different sample-level learning states. We propose Self-Routing, a behavior-conditioned post-training framework that uses rollout correctness and confidence to decide how each sample should be optimized. Depending on its behavior state, a sample is routed to GRPO, on-policy self-distillation, regularization, or skipping, allowing training to adapt without external teachers, extra annotations, or additional sampling. Experiments on mathematical reasoning acros

Read original source ↗ Open in workspace

recordType

paper

region

Global