LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
- Published
- Source
- arXiv
- Paper number
- 850
- Field
- LLMs / NLP
- arXiv ID
- 2608.06867
Key points
- It proposes a unified framework that decomposes routers into five components, allowing more than 16 heterogeneous routers to be compared in the same language.
- It automatically runs 18 models across a range of benchmark tasks to build routing evaluation data, xRouteBench, covering general NLP, vision, time series, and personalization.
- The learned router improves by 14.6% relative to fixed model selection. However, when the cost constraint gets tight, the lighter router wins.
- User-specific routing consistently produces personalization gains, but only when the user context is modeled well.
- It releases the open-source LLMRouter library so that new routers can be added in a few lines.
Paper links
External research summaries. These are not HDATF publications or measured product results.