AI Framework Optimizes UAV Logistics and Edge Computing

A new research paper introduces an agentic AI framework that combines large language models (LLMs) with chain-of-thought reasoning to address hybrid scheduling problems in cloud manufacturing. The framework coordinates unmanned aerial vehicles (UAVs) for both physical logistics—collecting finished products from manufacturing stations and transporting them to a central depot—and mobile edge computing (MEC), where computational tasks from industrial sensors are processed locally, on UAVs, or offloaded to the cloud. The coupling of routing decisions with computational task scheduling creates complexity: UAVs can only provide MEC services during service windows at stations, and routing affects energy budgets and resource availability under task deadlines. The proposed approach leverages LLMs to generate and evaluate scheduling solutions, using chain-of-thought reasoning to handle constraints. The paper is available on arXiv under identifier 2605.13221.