SOURCE-LINKED INTELLIGENCE

Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

On-premise assistants can give factory workers conversational access to machine documentation, but models capable of the task rarely fit shop-floor hardware. We show that after structural compression and retrieval-grounded adaptation, model size is no longer a reliable predictor of adapted answer quality: general capability falls almost linearly with parameter count, while judged retrieval-augmented answer quality does not. We therefore treat deployment as a post-adaptation selection problem, committing one sub-network per device on judged answer quality and measured on-device throughput under

Read original source ↗ Open in workspace

recordType

paper

region

Global