Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A4FN: an Agentic AI Architecture for Autonomous Flying Networks

André Coelho, Pedro Ribeiro, Helder Fontes, Rui Campos

TL;DR

The paper addresses the need for autonomous, context-aware management of Flying Networks (FNs) in dynamic, infrastructure-limited scenarios by introducing A4FN, an agentic AI architecture with a Perception Agent (PA) and a Decision-and-Action Agent (DAA). PA semantically interprets multimodal UAV data to derive real-time SLSs, while DAA autonomously reconfigures UAV placement, resource allocation, and network slicing to fulfill inferred intents. Key contributions include dynamic SLS generation, LLM-based semantic reasoning for intent translation, real-time resource orchestration, and interoperability with 6G/Wi-Fi 8 and SDN/NFV/MEC frameworks, along with a detailed roadmap of research challenges. The approach promises resilient, scalable, self-managing networks capable of operating in mission-critical contexts such as disaster response, potentially enabling AGI-native telecom infrastructure through integrated perception, reasoning, and actuation.

Abstract

This position paper presents A4FN, an Agentic Artificial Intelligence (AI) architecture for intent-driven automation in Flying Networks (FNs) using Unmanned Aerial Vehicles (UAVs) as access nodes. A4FN leverages Generative AI and Large Language Models (LLMs) to enable real-time, context-aware network control via a distributed agentic system. It comprises two components: the Perception Agent (PA), which semantically interprets multimodal input -- including imagery, audio, and telemetry data -- from UAV-mounted sensors to derive Service Level Specifications (SLSs); and the Decision-and-Action Agent (DAA), which reconfigures the network based on inferred intents. A4FN embodies key properties of Agentic AI, including autonomy, goal-driven reasoning, and continuous perception-action cycles. Designed for mission-critical, infrastructure-limited scenarios such as disaster response, it supports adaptive reconfiguration, dynamic resource management, and interoperability with emerging wireless technologies. The paper details the A4FN architecture, its core innovations, and open research challenges in multi-agent coordination and Agentic AI integration in next-generation FNs.

A4FN: an Agentic AI Architecture for Autonomous Flying Networks

TL;DR

The paper addresses the need for autonomous, context-aware management of Flying Networks (FNs) in dynamic, infrastructure-limited scenarios by introducing A4FN, an agentic AI architecture with a Perception Agent (PA) and a Decision-and-Action Agent (DAA). PA semantically interprets multimodal UAV data to derive real-time SLSs, while DAA autonomously reconfigures UAV placement, resource allocation, and network slicing to fulfill inferred intents. Key contributions include dynamic SLS generation, LLM-based semantic reasoning for intent translation, real-time resource orchestration, and interoperability with 6G/Wi-Fi 8 and SDN/NFV/MEC frameworks, along with a detailed roadmap of research challenges. The approach promises resilient, scalable, self-managing networks capable of operating in mission-critical contexts such as disaster response, potentially enabling AGI-native telecom infrastructure through integrated perception, reasoning, and actuation.

Abstract

This position paper presents A4FN, an Agentic Artificial Intelligence (AI) architecture for intent-driven automation in Flying Networks (FNs) using Unmanned Aerial Vehicles (UAVs) as access nodes. A4FN leverages Generative AI and Large Language Models (LLMs) to enable real-time, context-aware network control via a distributed agentic system. It comprises two components: the Perception Agent (PA), which semantically interprets multimodal input -- including imagery, audio, and telemetry data -- from UAV-mounted sensors to derive Service Level Specifications (SLSs); and the Decision-and-Action Agent (DAA), which reconfigures the network based on inferred intents. A4FN embodies key properties of Agentic AI, including autonomy, goal-driven reasoning, and continuous perception-action cycles. Designed for mission-critical, infrastructure-limited scenarios such as disaster response, it supports adaptive reconfiguration, dynamic resource management, and interoperability with emerging wireless technologies. The paper details the A4FN architecture, its core innovations, and open research challenges in multi-agent coordination and Agentic AI integration in next-generation FNs.

Paper Structure

This paper contains 16 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Agentic AI Architecture for Autonomous Flying Networks
  4. Conceptual Architecture
  5. Key Innovations
  6. Potential applications
  7. Alignment with State-of-the-Art
  8. Challenges and Research Directions
  9. Agent Instantiation and Deployment Models
  10. Multimodal Perception and Context Awareness
  11. Semantic Reasoning and Intent Translation
  12. Inter-Agent Coordination and Synchronization
  13. Energy Efficiency and Resource-Constrained Inference
  14. Scalability, Simulation, and Validation Environments
  15. Cross-Cutting Challenges
  16. ...and 1 more sections

Figures (2)

  • Figure 1: Deployment of a flying network providing wireless connectivity in a disaster response scenario.
  • Figure 2: Illustration of the A4FN conceptual architecture.