metadata
license: mit
pipeline_tag: text-generation
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
Charlie Zhang, Graham Neubig, Xiang Yue
Carnegie Mellon University, Language Technologies Institute
This repository contains post-training related checkpoints in extrapolation tasks.
Code: GitHub Repository
📚 Citation
If you find this work or code useful, please consider citing:
@misc{zhang2025interplaypretrainingmidtrainingrl,
title={On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models},
author={Charlie Zhang and Graham Neubig and Xiang Yue},
year={2025},
eprint={2512.07783},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2512.07783},
}