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

• URL: http://arxiv.org/abs/2609.01422v1
• Date: Tue, 01 Sep 2026 15:36:26 GMT
• Title: From Rollouts to Recipes: Self-Contained Post-Training for LLMs
• Abstract summary: Self-Routing is a behavior-conditioned post-training framework that uses rollout correctness and confidence to decide how each sample should be optimized.<n>We show that Self-Routing consistently improves over uniform GRPO, uniform OPSD, fixed mixtures, and simpler routing baselines.
• Score: 11.440101032760042
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity [5.35852583397955]
  On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student.<n>We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten.
  arXiv  Detail & Related papers  (2026-06-24T17:59:02Z)
• Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior [58.751981587234916]
  This paper formalizes the Refinement Provenance Inference (RPI) audit task as Refinement Provenance Inference (RPI)<n>We propose RePro, a logit-based framework that fuses teacher-forced likelihood features with logit-ranking signals.<n>During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access.
  arXiv  Detail & Related papers  (2026-01-05T10:16:41Z)
• VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL [38.782188833641676]
  Group-based policy optimization methods like GRPO and GSPO have become standard for training multimodal models.<n>They suffer from a critical emphgradient vanishing problem when all responses within a group receive identical rewards.<n>We propose textbfVADE, a sampling framework via online sample-level difficulty textbfEstimation.
  arXiv  Detail & Related papers  (2025-11-24T08:59:54Z)
• Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training [47.26632817047513]
  Reinforcement learning applied to large language models (LLMs) for reasoning tasks is often bottlenecked by unstable gradient estimates.<n>We propose Reinforce-Ada, an adaptive sampling framework for online RL post-training of LLMs.<n>Unlike conventional two-stage allocation methods, Reinforce-Ada interleaves estimation and sampling in an online successive elimination process.
  arXiv  Detail & Related papers  (2025-10-06T16:34:09Z)
• AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners [35.730489673985936]
  Self-Taughters (STaR) is an integral part of the training pipeline of self-improving reasoning Language Models (LMs)<n>We introduce Adaptive STaR (AdaSTaR), a novel algorithm that rectifies this by integrating two adaptive sampling principles.<n>AdaSTaR achieves best test accuracy in all instances and reduces training FLOPs by an average of 58.6% against an extensive list of baselines.
  arXiv  Detail & Related papers  (2025-05-22T07:24:11Z)
• Test-Time Alignment via Hypothesis Reweighting [56.71167047381817]
  Large pretrained models often struggle with underspecified tasks.<n>We propose a novel framework to address the challenge of aligning models to test-time user intent.
  arXiv  Detail & Related papers  (2024-12-11T23:02:26Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Semantic Self-adaptation: Enhancing Generalization with a Single Sample [45.111358665370524]
  We propose a self-adaptive approach for semantic segmentation. It fine-tunes the parameters of convolutional layers to the input image using consistency regularization. Our empirical study suggests that self-adaptation may complement the established practice of model regularization at training time.
  arXiv  Detail & Related papers  (2022-08-10T12:29:01Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• One for More: Selecting Generalizable Samples for Generalizable ReID Model [92.40951770273972]
  This paper proposes a one-for-more training objective that takes the generalization ability of selected samples as a loss function. Our proposed one-for-more based sampler can be seamlessly integrated into the ReID training framework.
  arXiv  Detail & Related papers  (2020-12-10T06:37:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.