paper-with-me

Papers

Switchcraft: AI Model Router for Agentic Tool Calling

2026-05-08 · Sharad Agarwal, Pooria Namyar, Alec Wolman, Rahul Ambavat, Ankur Gupta, Qizheng Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.07112

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tool Forge: A Validation-Carrying Toolchain for Governed Agentic Execution

2026-05-27 · Swanand Rao arxiv

Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting inside enterprise systems. Yet the tool layer on which this execution …

On the Robustness of Agentic Function Calling

2025-04-01 · Ella Rabinovich, Ateret Anaby-Tavor

Large Language Models (LLMs) are increasingly acting as autonomous agents, with function calling (FC) capabilities enabling them to invoke specific tools for tasks. While prior research has primarily focused on improving…

On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset

2025-10-27 · Vishvesh Bhat, Omkar Ghugarkar, Julian McAuley arxiv

Generalization across Agentic tool-calling environments remains a key unsolved challenge in developing reliable agentic reasoning systems. While large language models (LLMs) demonstrate strong performance on isolated ben…

MAVEN: Improving Generalization in Agentic Tool Calling

2026-05-29 · Omkar Ghugarkar, Vishvesh Bhat, Muhammad Ahmed Mohsin, Asad Aali arxiv

Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language models achieve strong results on individual benchmarks, their ability to…

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

2026-04-22 · Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis, Seshu Tirupathi 외 arxiv

The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and …