@article{reinforcementlearningforllmbasedmultiage,
  title = {Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces},
  author = {Chenchen Zhang},
  year = {2026},
  eprint = {2605.02801},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.02801},
}