Metraipolis › archive › dc_7d98537b2abb

Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing — arXiv:2609.37402

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37402
License (as archived): CC0-1.0
Archived: 2026-10-07T16:23:51.997Z
SHA-256 of the archived text: 32fc092c89199a6648ca807e0f344da328c38d1e3c48e602e01a34c38c845b57
Stable URL of this page: https://metraipolis.com/documento/dc_7d98537b2abb

How to cite

Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing — arXiv:2609.37402 — arXiv (en), https://arxiv.org/abs/2609.37402 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d98537b2abb (Metraipolis archive dc_7d98537b2abb, sha256 32fc092c89199a6648ca807e0f344da328c38d1e3c48e602e01a34c38c845b57)

BibTeX

@misc{dc7d98537b2abb,
  title = {Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing — arXiv:2609.37402},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37402},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d98537b2abb; sha256 32fc092c89199a6648ca807e0f344da328c38d1e3c48e602e01a34c38c845b57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37402. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37402 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.625Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).