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

TL;DR

This paper introduces a flexible, efficient, and adaptive framework for low-altitude edge intelligence that transforms high-level prompts into executable workflows using modular agents and real-time inference planning.

Contribution

The paper proposes the P2AECF framework, enabling dynamic, resource-aware, and prompt-driven edge cognition with modular agents and adaptive inference strategies.

Findings

Demonstrates adaptive, modular edge intelligence in low-altitude aerial networks.

Shows improved flexibility and resource efficiency over static inference pipelines.

Validates the framework through a real-world low-altitude aerial collaboration case.

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.