@article{fromfeedbackloopstopolicyupdatesreinforc,
  title = {From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery},
  author = {Lingzhe Zhang and Tong Jia and Yunpeng Zhai and Zixuan Xie and Chiming Duan and Minghua He and Philip S. Yu and Ying Li},
  year = {2026},
  eprint = {2605.15412},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.15412},
}