Switchcraft: AI Model Router for Agentic Tool Calling

arXiv:2605.00737v1 Announce Type: new Abstract: Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always

arXiv:2605.06890v1 Announce Type: new Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures

arXiv:2610.02762v1 Announce Type: new Abstract: Dynamic LLM routers promise to cut inference costs by sending each query to the cheapest model that can answer it correctly. We

arXiv:2605.01214v1 Announce Type: new Abstract: This position paper argues that agentic AI systems should be designed and evaluated as \emph{marginal token allocation economies}

arXiv:2604.22748v1 Announce Type: new Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment

arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers.

arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases,

arXiv:2608.26199v1 Announce Type: new Abstract: We ask whether AI agents powered by locally deployed large language models can reliably automate expert-defined hardware design