Metraipolis › archive › dc_706b69d7d02c

Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing — arXiv:2609.37362

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37362
License (as archived)
CC0-1.0
Archived
2026-10-07T16:23:49.610Z
SHA-256 of the archived text
9a811827c11f4d5c9187d515ab91cdbaec577081e8d075509069c122e920fb9e
Stable URL of this page
https://metraipolis.com/documento/dc_706b69d7d02c

How to cite

Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing — arXiv:2609.37362 — arXiv (en), https://arxiv.org/abs/2609.37362 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_706b69d7d02c (Metraipolis archive dc_706b69d7d02c, sha256 9a811827c11f4d5c9187d515ab91cdbaec577081e8d075509069c122e920fb9e)
BibTeX
@misc{dc706b69d7d02c,
  title = {Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing — arXiv:2609.37362},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37362},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_706b69d7d02c; sha256 9a811827c11f4d5c9187d515ab91cdbaec577081e8d075509069c122e920fb9e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37362. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--efficiency trade-off of LLM inference. Existing routers are typically learned through local fitting: a router is optimized for a particular query workload and candidate pool, and often requires additional supervision or retraining as the routing environment changes. We ask whether LLM routing can instead be approached from a foundation-model perspective, learning a reusable routing capability that generalizes across tasks, candidate models, and deployment conditions. To this end, we introduce RouteFM, which learns to characterize anonymous candidate models from behavioral context and infer their target-specific capabilities, rather than binding routing decisions to fixed model identities or a single environment. Through episodic pretraining across heterogeneous routing environments, this capability can be reused by a frozen router and adapted to new environments through context alone. Experiments demonstrate transfer across changes in domains, modalities, candidate pools, and context budgets, with the largest gains when behavioral evidence is limited. On MMR-Bench, which is excluded from pretraining, RouteFM outperforms the strongest baseline by 2.23 quality points with only eight observations per candidate. These results support moving LLM routing from repeated local fitting toward a pretrain once, route anywhere paradigm. 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/2609.37362 — 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 2026-10-07T15:54:53.621Z 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).