@article{policyconditionedcounterfactualcreditfor,
  title = {Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents},
  author = {Renwei Meng},
  year = {2026},
  eprint = {2606.05263},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.05263},
}