Saved in:
Bibliographic Details
Main Authors: Chwa, Channe, Wu, Xinle, Lu, Yao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.18773
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915875268853760
author Chwa, Channe
Wu, Xinle
Lu, Yao
author_facet Chwa, Channe
Wu, Xinle
Lu, Yao
contents LLM post-training pipelines that combine supervised fine-tuning and reinforcement learning are difficult to configure under realistic compute budgets: the configuration space is high-dimensional and heterogeneous, stages are strongly coupled, and each end-to-end evaluation is expensive. We propose AutoPipe, a budget-aware two-stage framework for configuration selection in LLM post-training. Offline, AutoPipe learns a dataset-conditioned learning-to-rank surrogate from historical runs, capturing within-dataset preferences and providing transferable guidance toward promising regions of the configuration space. Online, for a new dataset, AutoPipe uses the offline guidance to steer Bayesian optimization and models dataset-specific deviations with a Gaussian-process residual surrogate. To reduce evaluation cost, each trial is early-stopped and scored by a learned predictor that maps early training signals to a low-cost proxy for final post-training performance. Experiments on biomedical reasoning tasks show that AutoPipe consistently outperforms offline-only baselines and achieves comparable performance with the strongest online HPO baselines while using less than 10\% of their computational cost.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18773
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automatic Configuration of LLM Post-Training Pipelines
Chwa, Channe
Wu, Xinle
Lu, Yao
Machine Learning
Artificial Intelligence
LLM post-training pipelines that combine supervised fine-tuning and reinforcement learning are difficult to configure under realistic compute budgets: the configuration space is high-dimensional and heterogeneous, stages are strongly coupled, and each end-to-end evaluation is expensive. We propose AutoPipe, a budget-aware two-stage framework for configuration selection in LLM post-training. Offline, AutoPipe learns a dataset-conditioned learning-to-rank surrogate from historical runs, capturing within-dataset preferences and providing transferable guidance toward promising regions of the configuration space. Online, for a new dataset, AutoPipe uses the offline guidance to steer Bayesian optimization and models dataset-specific deviations with a Gaussian-process residual surrogate. To reduce evaluation cost, each trial is early-stopped and scored by a learned predictor that maps early training signals to a low-cost proxy for final post-training performance. Experiments on biomedical reasoning tasks show that AutoPipe consistently outperforms offline-only baselines and achieves comparable performance with the strongest online HPO baselines while using less than 10\% of their computational cost.
title Automatic Configuration of LLM Post-Training Pipelines
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.18773