@article{optimizingragrerankerswithllmfeedbackvia,
  title = {Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning},
  author = {Yuhang Wu and Xiangqing Shen and Fanfan Wang and Cangqi Zhou and Zhen Wu and Xinyu Dai and Rui Xia},
  year = {2026},
  eprint = {2604.02091},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.02091},
}