@article{reinforcingmultiturnreasoninginllmagents,
  title = {Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment},
  author = {Quan Wei and Siliang Zeng and Chenliang Li and Zhongruo Wang and William Brown and Oana Frunza and Wei Deng and Anderson Schneider and Yuriy Nevmyvaka and Yang Katie Zhao and Alfredo Garcia and Mingyi Hong},
  year = {2025},
  eprint = {2505.11821},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.11821},
}