| title | Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing |
|---|---|
| authors | Guannan Lai, Gelin Bian, Hao-Xuan Ma, Jun-Peng Jiang, Long Chen, Jian-Dong Liu, Zhi-Hao Tan, Han-Jia Ye |
| date | 2026-09-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.37402 |
| affiliation | SinapisAI |
| upvotes | 16 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such a router, however, often requires executing multiple candidate models on historical queries to collect query--model quality feedback, creating a nontrivial supervision cost before deployment. Existing work largely focuses on serving-time efficiency, overlooking whether the resulting savings are sufficient to recover this upfront expenditure. We further observe that routing quality often saturates well before all query--model feedback is collected, suggesting that dense supervision can be economically over-provisioned. We propose SaveRouter, a sparse-supervision routing framework that selectively acquires informative model feedback and shares capability information across related queries, while retaining query-level refinement for fine-grained routing. We evaluate routing by jointly accounting for supervision expenditure and subsequent serving-time savings. Across four routing benchmarks, the main setting uses only about 33--41% of available training feedback while maintaining competitive or better routing quality, and reduces the break-even deployment volume by approximately 1.9--9.5 times compared with the fastest conventional router. Further analysis shows that acquiring more supervision is not always economically preferable: the supervision level that minimizes serving cost can differ from the one that achieves the earliest payback. Our code is publicly available at https://github.com/LAMDA-Model-Reuse/SaveRouter. |
cite
@misc{lai2026routing,
title={Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing},
author={Guannan Lai and Gelin Bian and Hao-Xuan Ma and Jun-Peng Jiang and Long Chen and Jian-Dong Liu and Zhi-Hao Tan and Han-Jia Ye},
year={2026},
eprint={2609.37402},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.37402}
}