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

September 01, 2026 ยท Grace Period ยท ๐Ÿ› EMNLP 2026

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Yifei Li, Lingling Zhang, Muye Huang, Zihan Ma, Jiashuai Liu, Jun Liu arXiv ID 2609.01422 Category cs.CL: Computation & Language Citations 0 Venue EMNLP 2026
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 9 years ago