An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing

TL;DR

This paper introduces an agentic AI framework that combines large language models and hierarchical reinforcement learning to optimize UAV-assisted logistics and computing in manufacturing, improving scheduling stability and task completion rates.

Contribution

It presents a novel integration of large language models with hierarchical reinforcement learning for hybrid UAV logistics and edge computing scheduling.

Findings

Hierarchical PPO achieves 99.6% product collection success in last 500 episodes.

The framework maintains 100% deadline satisfaction rate.

Simulation shows more stable performance than advantage actor-critic.

Abstract

In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with computational task scheduling. In this paper, UAVs collect finished products from manufacturing stations and transport them back to a central depot. Meanwhile, computational tasks generated by industrial sensor devices at these stations are processed locally, at UAVs, or offloaded via UAVs to the cloud. This coupling makes the problem challenging. A UAV can provide MEC services only during its service window at a station, so routing decisions directly determine when UAV-assisted offloading is available. Routing decisions also affect the UAV energy budget and the availability of onboard computing and communication resources for computational task execution under task deadline constraints. To address this, we propose an agentic-AI-assisted optimization framework with two components. First, we develop an agentic AI that combines large language models, retrieval-augmented generation, and chain-of-thought reasoning to translate user input into an interpretable mathematical formulation for the hybrid scheduling problem. Second, we design a hierarchical deep reinforcement learning approach based on proximal policy optimization (PPO), where the upper layer learns UAV routing and the lower layer optimizes per-slot task execution and resource allocation. Simulation results show that the proposed framework yields more consistent formulations, while the hierarchical PPO achieves full product collection in 99.6% of the last 500 episodes and maintains a 100% deadline satisfaction rate, with more stable performance than the advantage actor-critic approach.