LLMs are everywhere: Ubiquitous Utilization of AI Models through Air Computing

2025-03-02

AI Summary

To address the spatial and resource constraints imposed by insufficient ground-based 2D network infrastructure on ubiquitous deployment of large language models (LLMs) and generative AI applications, this paper proposes Air Computing—a novel three-dimensional aerial-edge computing architecture. It pioneers the deep integration of LLM inference with collaborative multi-layer drone swarm offloading. The architecture establishes a scalable, adaptive, and highly robust air-ground cooperative AI execution framework, incorporating edge intelligence, formation control, distributed inference scheduling, QoE-driven offloading optimization, and lightweight LLM deployment. Empirical evaluation in disaster emergency scenarios demonstrates >90% of tasks completed within seconds, and a threefold improvement in service continuity under communication outages. These results validate the feasibility and significant performance gains of airborne LLM services in mission-critical scenarios, effectively transcending traditional terrestrial network limitations.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

We are witnessing a new era where problem-solving and cognitive tasks are being increasingly delegated to Large Language Models (LLMs) across diverse domains, ranging from code generation to holiday planning. This trend also creates a demand for the ubiquitous execution of LLM-powered applications in a wide variety of environments in which traditional terrestrial 2D networking infrastructures may prove insufficient. A promising solution in this context is to extend edge computing into a 3D setting to include aerial platforms organized in multiple layers, a paradigm we refer to as air computing, to augment local devices for running LLM and Generative AI (GenAI) applications. This approach alleviates the strain on existing infrastructure while enhancing service efficiency by offloading computational tasks to the corresponding air units such as UAVs. Furthermore, the coordinated deployment of various air units can significantly improve the Quality of Experience (QoE) by ensuring seamless, adaptive, and resilient task execution. In this study, we investigate the synergy between LLM-based applications and air computing, exploring their potential across various use cases. Additionally, we present a disaster response case study demonstrating how the collaborative utilization of LLMs and air computing can significantly improve outcomes in critical situations.

Problem

• Extend edge computing to 3D aerial platforms for LLM execution.
• Enhance service efficiency by offloading tasks to air units.
• Improve disaster response using LLMs and air computing synergy.

Innovation

• Extend edge computing to 3D aerial platforms
• Offload LLM tasks to UAVs for efficiency
• Enhance QoE with adaptive air unit coordination