@article{whendensercreditisnotenoughevidencecalib,
  title = {When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training},
  author = {Yuanfan Li and Qi Zhou and Wenjing Duan and Lu Chen},
  year = {2026},
  eprint = {2606.05885},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.05885},
}