Prompt-Driven Low-Altitude Edge Intelligence: Modular Agents and Generative Reasoning

2026-02-15

AI Summary

This work addresses the challenges of deploying large AI models in low-altitude edge intelligence, where rigid task structures, high resource demands, and static inference pipelines hinder adaptability to dynamic environments. To overcome these limitations, the authors propose the P2AECF framework, which leverages semantic prompts to automatically translate high-level tasks into executable inference workflows. P2AECF introduces three novel mechanisms: prompt-defined cognition, modular agent-based dynamic scheduling, and diffusion-controlled reasoning planning, collectively enabling model-agnostic, resource-aware, and context-adaptive edge intelligence. Experimental results demonstrate that P2AECF exhibits strong adaptability, modularity, and scalability within low-altitude intelligent networks, significantly enhancing the execution efficiency of real-time collaborative tasks.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Embodied AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

The large artificial intelligence models (LAMs) show strong capabilities in perception, reasoning, and multi-modal understanding, and can enable advanced capabilities in low-altitude edge intelligence. However, the deployment of LAMs at the edge remains constrained by some fundamental limitations. First, tasks are rigidly tied to specific models, limiting the flexibility. Besides, the computational and memory demands of full-scale LAMs exceed the capacity of most edge devices. Moreover, the current inference pipelines are typically static, making it difficult to respond to real-time changes of tasks. To address these challenges, we propose a prompt-to-agent edge cognition framework (P2AECF), enabling the flexible, efficient, and adaptive edge intelligence. Specifically, P2AECF transforms high-level semantic prompts into executable reasoning workflows through three key mechanisms. First, the prompt-defined cognition parses task intent into abstract and model-agnostic representations. Second, the agent-based modular execution instantiates these tasks using lightweight and reusable cognitive agents dynamically selected based on current resource conditions. Third, the diffusion-controlled inference planning adaptively constructs and refines execution strategies by incorporating runtime feedback and system context. In addition, we illustrate the framework through a representative low-altitude intelligent network use case, showing its ability to deliver adaptive, modular, and scalable edge intelligence for real-time low-altitude aerial collaborations.

Problem

• low-altitude edge intelligence
• large artificial intelligence models
• edge deployment constraints
• task flexibility
• real-time adaptability

Innovation

• Prompt-Driven Reasoning
• Modular Cognitive Agents
• Edge Intelligence
• Diffusion-Controlled Inference
• Low-Altitude Aerial Networks