cs.DCNov 6, 2026

Continual Instruction Tuning for LLM-based Management of Continuum Resources

Authors: Lanpei Li, Antonino Vaccarella, Vincenzo Lomonaco, Massimo Coppola

Organizations: Institute of Information Science and Technologies “Alessandro Faedo”, National Research Council (ISTI-CNR), Pisa, Italy · Department of Computer Science, University of Pisa, Pisa, Italy · Department of AI, Data and Decision Sciences, LUISS University, Rome, Italy

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.

Figures & tables

Explore similar work

CardsList
  1. Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management

    Sep 8, 2026Antonino Vaccarella, Lanpei Li, Vincenzo Lomonaco +1Language Model-Based ControlLLM-Guided RL

  2. Self-Indexing Latent Memories for Access-Aware Continual Instruction Tuning of LLMs

    Nov 8, 2026Dhruv Dixit, Paritosh Pandey, Snehalkumar 'Neil' S. GaikwadContinual Learning for LLMsInstruction Tuning

  3. Training Language Models to Cooperate with Inference-Time Controllers

    Jul 26, 2026Moumita Choudhury, Vanshaj Khattar, Jing Liu +4RL for Language Model ReasoningLLM Post-Training