@article{
wang2026reinforcement,
title={Reinforcement Learning for {LLM} Post-Training: A Survey},
author={Zhichao Wang and Kiran Ramnath and Bin Bi and Shiva Kumar Pentyala and SOUGATA CHAUDHURI and Shubham Mehrotra and Xiang-Bo Mao and James Zhu and Sitaram Asur and Claire Na Cheng},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=UdsXTNzzvg},
note={}
}