Towards Edge General Intelligence via Large Language Models: Opportunities and Challenges

TL;DR

This paper surveys the integration of Large Language Models into Edge Intelligence, highlighting opportunities, challenges, and system architectures to advance towards Edge General Intelligence with practical implementation insights.

Contribution

It categorizes EGI systems into centralized, hybrid, and decentralized frameworks, reviewing existing implementations and evaluating small language models for edge deployment.

Findings

Identifies three conceptual EGI system architectures.

Reviews current implementations and frameworks.

Evaluates performance of small language models on edge devices.

Abstract

Edge Intelligence (EI) has been instrumental in delivering real-time, localized services by leveraging the computational capabilities of edge networks. The integration of Large Language Models (LLMs) empowers EI to evolve into the next stage: Edge General Intelligence (EGI), enabling more adaptive and versatile applications that require advanced understanding and reasoning capabilities. However, systematic exploration in this area remains insufficient. This survey delineates the distinctions between EGI and traditional EI, categorizing LLM-empowered EGI into three conceptual systems: centralized, hybrid, and decentralized. For each system, we detail the framework designs and review existing implementations. Furthermore, we evaluate the performance and throughput of various Small Language Models (SLMs) that are more suitable for development on edge devices. This survey provides researchers with a comprehensive vision of EGI, offering insights into its vast potential and establishing a foundation for future advancements in this rapidly evolving field.