Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarks

英文标题：Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarks

arXiv:2608.14641v1 Announce Type: new Abstract: Agentic systems increasingly delegate model selection to a router, yet open-source routers are usually evaluated with different tasks, candidate pools, and execution protocols, limiting direct comparison. We present a common measurement protocol and h

2.1 KB 640 B 612 B 380 B 9.1 KB 32.7 KB 22.8 KB 24.2 KB 34.7 KB