Is Serving-Time Language-Model Inference Necessary for Recommendation? Evidence from Generative and Agentic Settings
The study challenges whether strong recommendation performance requires real-time language model inference by introducing LIME-Rec, a lightweight recovery test. LIME-Rec combines three independent experts—sequential, collaborative, and semantic—to see if accuracy can be achieved without complex serving mechanisms. Findings show that alternatives using offline item representations and transparent fusion can match or exceed LM systems.