Explainable Model Routing for Agentic Workflows
This addresses the need for explainability in AI agent routing for developers, though it appears incremental as it builds on existing routing architectures by adding interpretability components.
The paper tackles the problem of uninterpretable model routing in agentic workflows by introducing Topaz, a framework that replaces silent model assignments with an inherently interpretable router, enabling users to audit system logic and tune cost-quality tradeoffs.
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.