@article{forgequalityawarereinforcementlearningfo,
  title = {Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs},
  author = {Xiaozhe Li and Xinyu Fang and Shengyuan Ding and Yang Li and Linyang Li and Haodong Duan and Qingwen Liu and Kai Chen},
  year = {2026},
  eprint = {2605.08905},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.08905},
}