@article{incentivizingconsistenteffectiveandscala,
  title = {Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards},
  author = {Jiajun Fan and Roger Ren and Jingyuan Li and Rahul Pandey and Prashanth Gurunath Shivakumar and Ivan Bulyko and Ankur Gandhe and Ge Liu and Yile Gu},
  year = {2025},
  eprint = {2510.20867},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.20867},
}