[2606.13241] Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm

-->

Computer Science > Artificial Intelligence

arXiv:2606.13241 (cs)

[Submitted on 11 Jun 2026]

Title:Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm

Authors:Francesco Massa, Marco Cristofanilli<br>View a PDF of the paper titled Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm, by Francesco Massa and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Defining query difficulty is one of the hardest problems in deployment engineering. Existing LLM routers rely on surface features such as domain labels, keywords, and token count, ignoring the within-domain variance that actually determines model success. Frontier models cost ten to one hundred times more than local open-weight models, so at production scale even small per-request savings become a direct cloud-bill lever. We present Brick, a multimodal router that scores each model on six capability dimensions, combines this with a per-query difficulty estimate, and dispatches via a cost-penalized geometric rule. A continuous preference knob lets operators slide between max-quality and max-saving profiles at deploy time. On a benchmark of 5,504 queries, Brick at max-quality reaches 76.98% accuracy, beating the best single model (75.02%) and all tested routers. At a neutral cost-quality profile, Brick achieves 74.11% accuracy at 4.71x lower cost than always using the strongest model. At min-cost, it cuts cost 22.15x with 11.85 points accuracy loss. Median latency drops from 51.2s to 22.8s.

Comments:<br>17 pages, 5 figures. Technical report

Subjects:

Artificial Intelligence (cs.AI)

ACM classes:<br>I.2.7; I.2.6; I.2.11; C.2.4

Cite as:<br>arXiv:2606.13241 [cs.AI]

(or<br>arXiv:2606.13241v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.13241

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Francesco Massa [view email]<br>[v1]<br>Thu, 11 Jun 2026 11:54:07 UTC (975 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm, by Francesco Massa and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)