Metraipolis › archive › dc_e40d3f25d2ae

Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems — arXiv:2611.05275

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05275
License (as archived)
CC0-1.0
Archived
2026-11-04T19:04:56.114Z
SHA-256 of the archived text
b72bb4406ff4568b6cf81ddcea0f9d6af51791f0f472166a44adf8b909194fdc
Stable URL of this page
https://metraipolis.com/documento/dc_e40d3f25d2ae

How to cite

Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems — arXiv:2611.05275 — arXiv (en), https://arxiv.org/abs/2611.05275 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e40d3f25d2ae (Metraipolis archive dc_e40d3f25d2ae, sha256 b72bb4406ff4568b6cf81ddcea0f9d6af51791f0f472166a44adf8b909194fdc)
BibTeX
@misc{dce40d3f25d2ae,
  title = {Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems — arXiv:2611.05275},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05275},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e40d3f25d2ae; sha256 b72bb4406ff4568b6cf81ddcea0f9d6af51791f0f472166a44adf8b909194fdc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05275. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artificial general intelligence (AGI) requires a method that can understand, generate, reason, and act across diverse domains and modalities. Rather than relying on a single model to master every capability, a promising path toward AGI now is to orchestrate a heterogeneous ecosystem of specialized models, tools, and policies (candidates) into a unified AI system. At the heart of this vision lies a fundamental question: how can an AI system dynamically select and coordinate the most capable candidate for each task while balancing performance and computational cost? In this work, we present Route Anything, a unified framework for studying model and policy routing across general-purpose AI systems. We develop a unified theoretical foundation that characterizes optimal routing under quality--cost trade-offs and establishes how the information available to a router determines its attainable performance. To systematically investigate routing across diverse capabilities, we first construct an omni-modal trajectory matrix spanning 25 benchmarks across language understanding, image, video, and speech generation, coding and workplace agents, and robotic manipulation, comprising 374,401 scored runs from 452 candidate configurations. Building on this framework, we train and test different routers to investigate the potential of omni-modal model routing, the capabilities of learned routers, and the conditions under which routing improves efficiency. Our results reveal substantial opportunities for capability orchestration: per-input oracle routing outperforms the best fixed candidate by 5.4 points, and learned routers outperform it by 0.3 points across 16 benchmarks, by 2.1 points on video generation, and by 1.1 points on robot manipulation while using 24% less policy time. More importantly, routing raises efficiency by 8.82x on average compared with the reference model.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.05275 — 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 2026-11-04T18:39:37.581Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).