@article{primepolicyreinforcediterativemultiagent,
  title = {PRIME: Policy-Reinforced Iterative Multi-agent Execution for Algorithmic Reasoning in Large Language Models},
  author = {Jiawei Xu and Zhenyu Yu and Ziqian Bi and Minh Duc Pham and Xiaoyi Qu and Danyang Zhang},
  year = {2026},
  eprint = {2602.11170},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.11170},
}