@article{reinforcementlearningtoimprovelargelangu,
  title = {Reinforcement learning to improve large language model-based automated code compliance systems},
  author = {Jack Wei Lun Shi and Minghao Dang and Wawan Solihin and Leong Hien Poh and Justin K. W. Yeoh},
  year = {2026},
  eprint = {2606.22402},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.22402},
}