@inproceedings{chen-etal-2026-efficient-hyperparameter,
    title = "Efficient Hyperparameter Optimization for {LLM} Reinforcement Learning",
    author = "Chen, Minping  and
      Xiao, Bowen  and
      Liang, Du  and
      Zeng, Chuxuan  and
      Wen, Zeyi",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1271/",
    pages = "27540--27552",
    ISBN = "979-8-89176-390-6",
    abstract = "Hyperparameters are critical to LLM reinforcement learning (RL), but existing hyperparameter optimization (HPO) methods remain inefficient in this area, due to the massive model scale and resource-intensive training cycles. In this paper, we propose Joint Fidelity Hyperparameter Optimization (JF-HPO), which simultaneously adapts both model size and training budget as fidelity. JF-HPO is empowered by: (i) a small proxy model of the target LLM for efficient training and evaluation in each HPO trial; (ii) several carefully designed early-stopping strategies based on training dynamics; (iii) an efficient checkpointing mechanism to eliminate redundant computations. JF-HPO significantly improves the computational efficiency of each trial (up to 14.9$\times$) compared with existing HPO methods, thus achieving better predictive accuracy in most cases under the same time budget. Notably, JF-HPO delivers performance improvements ranging from 5.8{\%} to 111.6{\%} over VeRL Recipe."
}