@article{trolltrustregionsimprovereinforcementlea,
  title = {TROLL: Trust Regions improve Reinforcement Learning for Large Language Models},
  author = {Philipp Becker and Niklas Freymuth and Serge Thilges and Fabian Otto and Gerhard Neumann},
  year = {2025},
  eprint = {2510.03817},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.03817},
}