科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ arXiv2026-09-01· cs.CL

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

Yifei Li, Lingling Zhang, Muye Huang, Zihan Ma, Jiashuai Liu, Jun Liu

原始摘要(英文原文)· Original abstract
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 across Qwen3 and Qwen3.5 backbones show that Self-Routing consistently improves over uniform GRPO, uniform OPSD, fixed mixtures, and simpler routing baselines. Further analyses show that the routing distribution changes over training and reduces unnecessary updates on low-signal or already stable samples.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

From Rollouts to Recipes: Self-Contained Post-Training for LLMs — 科研速览 Science Skim