Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning

@misc{yang2026adaptive,
  title = {Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning},
  author = {Wei Yang and Defu Cao and Jiacheng Pang and Muyan Weng and Yan Liu},
  year = {2026},
  eprint = {2603.07972},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.07972},
}