@article{dynamicmodelroutingandcascadingforeffici,
  title = {Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey},
  author = {Yasmin Moslem and John D. Kelleher},
  year = {2026},
  eprint = {2603.04445},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.04445},
}