@article{reinforcementlearningforaligninglarge,
  title = {Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting},
  author = {Mohamed Salim Aissi and Clement Romac and Thomas Carta and Sylvain Lamprier and Pierre-Yves Oudeyer and Olivier Sigaud and Laure Soulier and Nicolas Thome},
  year = {2024},
  eprint = {2410.19920},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.19920v2},
}