Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding

@misc{wangTue Oct 14 2025 18:07:33 GMT+0000 (Coordinated Universal Time)reinforcementlearningoutofdistribution,
      title={Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding},
      author={Hanyin Wang and Zhenbang Wu and Gururaj Kolar and Hariprasad Korsapati and Brian Bartlett and Bryan Hull and Jimeng Sun},
      year={Tue Oct 14 2025 18:07:33 GMT+0000 (Coordinated Universal Time)},
      eprint={2505.21908},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2505.21908},
}