让智能体任务路由可解释，看清模型选择背后的权衡。
Explainable Model Routing for Agentic Workflows
- 用技能画像整合多基准表现，量化模型能力
- 路由决策全程可追溯，权衡成本与性能
- 自动生成自然语言解释，适合开发者调试
现代智能体工作流将复杂任务分解为专业化子任务，并将它们分配给不同模型以在不降低质量的前提下降低成本。然而，现有路由架构仅关注性能优化，未记录模型能力与成本之间的潜在权衡。缺乏明确依据时，开发者无法区分智能高效——为任务匹配专用模型——与因预算驱动导致的隐性失败。我们提出 Topaz 框架，为智能体路由引入正式可审计性。Topaz 将无声的模型分配替换为内在可解释的路由器，包含三个组件：(i) 基于技能的轮廓分析，将多种基准上的表现合成细粒度的能力画像；(ii) 完全可追踪的路由算法，利用基于预算和多目标优化生成清晰的决策路径，展示技能匹配分如何与成本权衡；(iii) 面向开发者的解释机制，将这些路径转化为自然语言，使用户能够审计系统逻辑并迭代调整成本-质量平衡。通过使路由决策可解释，Topaz 支持用户理解、信任并有意义地引导路由后的智能体系统。
原文摘要 · Abstract (English)
Modern agentic workflows decompose complex tasks into specialized subtasks and route them to diverse models to minimize cost without sacrificing quality. However, current routing architectures focus exclusively on performance optimization, leaving underlying trade-offs between model capability and cost unrecorded. Without clear rationale, developers cannot distinguish between intelligent efficiency -- using specialized models for appropriate tasks -- and latent failures caused by budget-driven model selection. We present Topaz, a framework that introduces formal auditability to agentic routing. Topaz replaces silent model assignments with an inherently interpretable router that incorporates three components: (i) skill-based profiling that synthesizes performance across diverse benchmarks into granular capability profiles (ii) fully traceable routing algorithms that utilize budget-based and multi-objective optimization to produce clear traces of how skill-match scores were weighed against costs, and (iii) developer-facing explanations that translate these traces into natural language, allowing users to audit system logic and iteratively tune the cost-quality tradeoff. By making routing decisions interpretable, Topaz enables users to understand, trust, and meaningfully steer routed agentic systems.
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。