@article{programlearningwithverifiablerewardssymb,
  title = {Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs},
  author = {Vishvesh Bhat},
  year = {2026},
  eprint = {2608.28421},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.28421},
}