@article{incontextreinforcementlearningfromsubopt,
  title = {In-Context Reinforcement Learning From Suboptimal Historical Data},
  author = {Juncheng Dong and Moyang Guo and Ethan X. Fang and Zhuoran Yang and Vahid Tarokh},
  year = {2026},
  eprint = {2601.20116},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.20116},
}