用空间能力路由提升大模型部署效率，降本增效。
Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm
- 基于六维能力评分+查询难度估算，动态分配最合适模型
- 成本-质量平衡下，成本降低4.71倍，准确率仍达74.11%
- 支持运行时切换质量与成本优先模式，适合生产环境部署
定义查询难度是部署工程中最难的问题之一。现有大模型路由依赖领域标签、关键词和词元数量等表面特征，忽略了同一领域内实际决定模型表现的差异。前沿模型成本是本地开源模型的十到一百倍，因此在生产规模下，每次请求的微小节省都会直接转化为云账单的显著降低。我们提出 Brick，一种多模态路由系统，对每个模型进行六维能力评分，结合查询难度估计，通过带成本惩罚的几何规则进行调度。一个连续偏好旋钮使运营者可在部署时自由切换最大质量与最大节省模式。在包含5,504个查询的基准测试中，Brick 在最大质量模式下达到76.98%准确率，超越最佳单模型（75.02%）及所有测试路由；在中性成本-质量配置下，准确率达74.11%，成本仅为始终使用最强模型的4.71倍；在最小成本模式下，成本降低22.15倍，准确率下降11.85个百分点，中位延迟从51.2秒降至22.8秒。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。