The field of edge computing and resource management is rapidly evolving, with a focus on developing innovative solutions to optimize performance, reduce latency, and improve efficiency. Recent research has explored the use of adaptive orchestration methods, intelligent resource allocation algorithms, and hierarchical prediction-based management frameworks to address the challenges of managing distributed systems and large language models. Notable advancements include the development of novel algorithms and systems that enable real-time resource configuration, dynamic workload distribution, and adaptive split inference. These innovations have the potential to significantly improve the efficiency and reliability of edge computing environments and cloud-based systems. Noteworthy papers include:

• Adaptive Orchestration for Inference of Large Foundation Models at the Edge, which proposes a novel adaptive orchestration method for managing distributed inference workloads.
• IntentContinuum: Using LLMs to Support Intent-Based Computing Across the Compute Continuum, which introduces a novel framework for intent-driven resource management using large language models.