@article{vimpovalueimplicitpolicyoptimizationforl,
  title = {VIMPO: Value-Implicit Policy Optimization for LLMs},
  author = {Zhewei Kang and Aosong Feng and Sergey Levine and Dawn Song and Xuandong Zhao},
  year = {2026},
  eprint = {2606.20008},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.20008},
}