@misc{lit_2610_34427,
  title = { {ScaleRLT: Exact Log-Probabilities and Fast Deferred Rollouts for Reinforcement Learning on Looped Transformers} },
  author = {Dezhen Lu and Zixiang Ni and Runguo Li},
  year = {2026},
  note = {arXiv preprint},
  eprint = {2610.34427},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.34427}
}