@article{chainofuncertainrewardswithlargelanguage,
  title = {Chain of Uncertain Rewards with Large Language Models for Reinforcement Learning},
  author = {Shentong Mo},
  year = {2026},
  eprint = {2604.13504},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.13504},
}