Metraipolis › archive › dc_0374aff70b44

SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks — arXiv:2608.12127

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12127
License (as archived)
CC0-1.0
Archived
2026-10-19T05:49:39.646Z
SHA-256 of the archived text
ee4ebc9d76e300aca3d736348ac4d29926cd4c8149d05378286978f679504c26
Stable URL of this page
https://metraipolis.com/documento/dc_0374aff70b44

How to cite

SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks — arXiv:2608.12127 — arXiv (en), https://arxiv.org/abs/2608.12127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0374aff70b44 (Metraipolis archive dc_0374aff70b44, sha256 ee4ebc9d76e300aca3d736348ac4d29926cd4c8149d05378286978f679504c26)
BibTeX
@misc{dc0374aff70b44,
  title = {SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks — arXiv:2608.12127},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12127},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0374aff70b44; sha256 ee4ebc9d76e300aca3d736348ac4d29926cd4c8149d05378286978f679504c26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA evaluation, lacks systematic calibration optimization for open-set scenarios, and employs training objectives that dilute multi-positive signals via softmax normalization without incorporating cost. We address these limitations with three contributions: (1)VLM-ExecRouterBench, the first execution-oriented VLM routing benchmark covering Code, Agentic, and Search domains with 11 candidate models spanning nearly two orders of magnitude in pricing; (2)SCOPE-Router, a dual-tower router that matches queries to model behavior profiles constructed via hybrid calibration (random/diagnostic/diversity sampling), enabling new models to join routing without retraining; (3)CRM+RCCR, an architecture-agnostic cost-aware objective that encodes cost preference into continuous relevance targets through per-pair independent scoring, eliminating multi-positive dilution while regularizing queries with similar routing preferences to be closer in the routing space. Empirically, SCOPE-Router achieves the best Rank Score on all three benchmarks, surpassing the runner-up by 1.84 points under OOD settings and by 6.75 points under doubly OOD open-set evaluation. When applied to four diverse routers, CRM+RCCR improves Rank Score by 1.25--6.21 points.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12127 — 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 2026-10-19T05:42:25.911Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).