@article{tokenbudgetawarepoolroutingforcosteffici,
  title = {Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference},
  author = {Huamin Chen and Xunzhuo Liu and Junchen Jiang and Bowei He and Xue Liu},
  year = {2026},
  eprint = {2604.09613},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.09613},
}