2 papers
cs.NI2026
Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment
Warren Johnson, Charles Lee
Selecting the appropriate model at inference time -- the routing problem -- requires jointly optimizing output quality, cost, latency, and governance constraints. Existing approach…
cs.CL2026
Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial
Warren Johnson, Charles Lee
The economics of prompt compression depend not only on reducing input tokens but on how compression changes output length, which is typically priced several times higher. We evalua…