@article{rewardevolutionwithgraphofthoughtsabilev,
  title = {Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning},
  author = {Changwei Yao and Xinzi Liu and Chen Li and Marios Savvides},
  year = {2025},
  eprint = {2509.16136},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.16136},
}