When a different LLM is substituted into an in-progress agent trajectory, the trajectory diverges almost immediately from the logged one, so replay-based routing benchmarks evaluate decisions against states that never occur.
Switchcraft: AI Model Router for Agentic Tool Calling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Model routing can mitigate this, but existing routers are designed for chat completion rather than tool use. We present Switchcraft, the first (to the best of our knowledge) model router optimized for agentic tool calling. Switchcraft operates inline, selecting the lowest-cost model subject to correctness. We construct an evaluation framework on five function-calling benchmarks and train a DistilBERT-based classifier, deployed under a latency budget. Switchcraft achieves 82.9% accuracy -- matching or exceeding the best individual model -- while reducing inference cost by 84%, saving over $3,600 per million queries. We find that larger models do not consistently outperform smaller ones on tool-use tasks, and that nominally cheaper models can incur higher total cost due to token-intensive reasoning. Our work enables cost-aware agentic AI deployment without sacrificing correctness.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World
When a different LLM is substituted into an in-progress agent trajectory, the trajectory diverges almost immediately from the logged one, so replay-based routing benchmarks evaluate decisions against states that never occur.