@inproceedings{mrpo2026,
  title = {Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning},
  author = {Jung, Junha and Jeong, Minbyul and Lim, Suhyeon and Jung, Sungwook and Yun, Jaehoon and Roh, Taeyun and Sung, Mujeen and Kang, Jaewoo},
  year = {2026},
  booktitle = {EMNLP 2026 Main},
  eprint = {2606.31825},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2606.31825},
  url = {https://arxiv.org/abs/2606.31825}
}