AIBullisharXiv – CS AI · Mar 176/10
🧠
Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference
Researchers propose Outcome-Aware Tool Selection (OATS), a method to improve tool selection in LLM inference gateways by interpolating tool embeddings toward successful query centroids without adding latency. The approach improves tool selection accuracy on benchmarks while maintaining single-digit millisecond CPU processing times.