Intent-Driven Task Coordination in Low-Altitude IoT Networks: Autonomous Cognitive Agents via LLMs and Distributed Active Inference

Abstract

Low-altitude Internet of Things (IoT) networks are emerging as an important platform for real-time monitoring, aerial logistics, and other distributed intelligent services. However, as missions become more complex and less structured, manual task decomposition and predefined coordination strategies no longer scale, leading to inefficiencies, long delays, and limited real-time adaptability. At the same time, existing deep reinforcement learning (DRL) methods rely on fixed reward formulations, which often incur prohibitive retraining costs when mission objectives or network conditions change. Addressing these challenges requires a paradigm that can transform high-level human intent into efficient multiagent task coordination and offloading under dynamic, resource-constrained conditions. To this end, we propose a generative AI framework that integrates large language models (LLMs) with distributed active inference (AIF) for intent-driven task graph generation and online resource scheduling. Specifically, a scenario-based iterative stream generation mechanism converts natural-language instructions into executable task graphs while mitigating context window exhaustion and structural hallucinations. Each uncrewed aerial vehicle (UAV) and edge server operates as an autonomous AIF agent that maintains a variational belief over hidden states coupled with the task graph, and minimizes expected free energy (EFE) from local noisy observations to optimize task offloading and mobility without centralized coordination or global retraining. Extensive experiments show that the proposed method consistently outperforms mainstream DRL benchmarks in convergence, robustness, and adaptability, demonstrating its effectiveness for dynamic low-altitude edge intelligence.