Instruction tuning improves large model control of cloud edge resources
Continual Instruction Tuning for LLM-ased Management of Continuum Resources
Distributed, Parallel, and Cluster ComputingMachine Learning
Summary
Managing computer resources across cloud and edge devices can be complicated and slow when large language models are directly used for quick decisions. The authors suggest using these models instead as smart translators that prepare instructions just once when goals or situations change, leaving faster systems to handle immediate tasks. They show that continually updating this translator with new instructions can forget old ones unless previous examples are replayed during training. This approach helps maintain good performance and is more flexible than simple grammar-based methods.
What this means in practice
- •For cloud infrastructure teams: Improve handling of shifting management goals by continually tuning an instruction compiler to work with existing fast control systems for resource allocation.
- •For network operations teams: Use an instruction-tuned model to translate management intents into commands that adapt quickly to network and workload changes without slowing down control loops.
Authors
Lanpei Li, Antonino Vaccarella, Vincenzo Lomonaco, Massimo Coppola
Abstract
Large language models (LLMs) are increasingly explored for resource management across the Cloud-Edge continuum. However, embedding LLMs directly inside latency-sensitive control loops places inference latency, execution jitter, and hallucination risks on the critical path. This study argues for a different use of LLMs: a continually instruction-tuned intent compiler that runs once per management intent or declared context change, above a fast, deterministic tactical controller that handles all low-latency runtime actions. We formulate intent compilation as a continual instruction tuning problem, because management intents arrive sequentially and accumulate while infrastructure and workload contexts drift. Unlike recent LLM-based management frameworks, our design scores the model's outputs by execution, so that catastrophic forgetting can be measured in the executed objective of the underlying controller. On a continuum simulator with a 2B backbone and parameter-efficient adapters, preliminary results show that naive sequential tuning forgets earlier intents in the executed objective, that replay of stored examples nearly prevents this forgetting, and that the tuned compact compiler performs on par with simpler translators while being more robust than a grammar parser to rephrased intents.