Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents
Read the original on arXiv AI →The paper presents a method for selecting sub‑networks of large language models for on‑premise factory assistants, showing that after structural compression and retrieval‑grounded adaptation, model size no longer predicts answer quality. By treating deployment as a post‑adaptation selection problem, the authors commit one sub‑network per device based on judged answer quality and measured on‑device throughput, while respecting a general‑capability floor and memory budget. A weight‑shared supernetwork trained with sandwich‑style in‑place distillation makes this selection inexpensive, and a manufacturing‑manual case study demonstrates that the approach recovers most of the quality loss while operating across heterogeneous edge tiers at low power.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.