LLM-Driven Causal Discovery for Monitoring Metrics in Computing Continuum Systems: A Comparative Study

Monitoring large-scale systems such as the Cloud–Edge–IoT continuum is challenging due to their distributed, heterogeneous, and evolving nature. Tracking all components—from cloud servers to IoT devices—demands intensive probe deployment and frequent data collection, causing network traffic, computation, and storage overhead. These challenges are intensified by the lack of prior knowledge about which metrics matter most, often leading to redundant monitoring. To address this, we explore whether Large Language Models (LLMs) can uncover causal relationships between metrics using only their textual descriptions. We propose a novel batch prompting strategy that allows LLMs to reason over multiple variables simultaneously, reducing query complexity while preserving interpretability. Our evaluation across several instruction-tuned LLMs shows stronger inter-model alignment than existing pairwise methods and reveals overlaps with causal graphs from traditional numerical algorithms. These results suggest that LLMs can support intelligent monitoring by identifying influential metrics and minimizing redundancy.