Score: 2

When to Reason: Semantic Router for vLLM

Published: October 9, 2025 | arXiv ID: 2510.08731v1

By: Chen Wang , Xunzhuo Liu , Yuhan Liu and more

BigTech Affiliations: IBM Tencent University of California, Berkeley

Potential Business Impact:

Smartly uses AI power, saving time and money.

Business Areas:
Semantic Search Internet Services

Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also incurs significant costs in inference latency and token usage, with environmental and financial impacts, which are unnecessary for many simple prompts. We present a semantic router that classifies queries based on their reasoning requirements and selectively applies reasoning only when beneficial. Our approach achieves a 10.2 percentage point improvement in accuracy on the MMLU-Pro benchmark while reducing response latency by 47.1% and token consumption by 48.5% compared to direct inference with vLLM. These results demonstrate that semantic routing offers an effective mechanism for striking a balance between accuracy and efficiency in open-source LLM serving systems

Country of Origin
πŸ‡¨πŸ‡³ πŸ‡ΊπŸ‡Έ United States, China

Page Count
7 pages

Category
Computer Science:
Emerging Technologies