RESEARCHInvestigateNEXT 12 MONTHS
AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
AgentWeave proposes a pre-routing strategy to reduce candidate tool sets before LLM inference, lowering prompt token costs and latency.
Open source