@article{breakingthesafetycapabilitytradeoffreinf,
  title = {Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs},
  author = {Dongkyu Derek Cho and Huan Song and Arijit Ghosh Chowdhury and Haotian An and Yawei Wang and Rohit Thekkanal and Negin Sokhandan and Sharlina Keshava and Hannah Marlowe},
  year = {2025},
  eprint = {2511.21050},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.21050},
}