@article{historyawarecrossattentionreinforcement,
  title = {History-Aware Cross-Attention Reinforcement: Self-Supervised Multi Turn and Chain-of-Thought Fine-Tuning with vLLM},
  author = {Andrew Kiruluta and Andreas Lemos and Priscilla Burity},
  year = {2025},
  eprint = {2506.11108},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.11108v1},
}