Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Feibo, Dong, Li, Pan, Xitao, Wang, Kezhi, Pan, Cunhua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908499209879552
author Jiang, Feibo
Dong, Li
Pan, Xitao
Wang, Kezhi
Pan, Cunhua
author_facet Jiang, Feibo
Dong, Li
Pan, Xitao
Wang, Kezhi
Pan, Cunhua
contents This paper proposes a novel Agentic Retrieval-augmented generation with Mamba-Attention Integrated Transformer (ARMAIT) framework for multi-Unmanned Aerial Vehicle (UAV) trajectory optimization. The framework is built upon Large Language Models (LLMs), incorporating Retrieval-Augmented Generation (RAG) empowered by Agentic AI and integrated with a UAV-specific knowledge base. Through the Agentic RAG, the LLM autonomously interprets high-level task requirements and identifies the key components necessary for trajectory optimization, including model inputs and outputs, network architecture, reward functions, and task constraints. To support efficient modeling across different system scales, we introduce the Mamba-Attention Integrated Transformer (MAIT), a hybrid neural architecture that combines the long-range dependency modeling capability of attention mechanisms with the efficient temporal dynamic representation of Mamba. Furthermore, a Trajectory-Group Relative Policy Optimization (T-GRPO) method is proposed to achieve unified policy gradient optimization in both discrete and continuous trajectory spaces for MAIT training. Extensive experimental results validate the feasibility and effectiveness of the proposed ARMAIT framework.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16379
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks
Jiang, Feibo
Dong, Li
Pan, Xitao
Wang, Kezhi
Pan, Cunhua
Information Theory
Signal Processing
This paper proposes a novel Agentic Retrieval-augmented generation with Mamba-Attention Integrated Transformer (ARMAIT) framework for multi-Unmanned Aerial Vehicle (UAV) trajectory optimization. The framework is built upon Large Language Models (LLMs), incorporating Retrieval-Augmented Generation (RAG) empowered by Agentic AI and integrated with a UAV-specific knowledge base. Through the Agentic RAG, the LLM autonomously interprets high-level task requirements and identifies the key components necessary for trajectory optimization, including model inputs and outputs, network architecture, reward functions, and task constraints. To support efficient modeling across different system scales, we introduce the Mamba-Attention Integrated Transformer (MAIT), a hybrid neural architecture that combines the long-range dependency modeling capability of attention mechanisms with the efficient temporal dynamic representation of Mamba. Furthermore, a Trajectory-Group Relative Policy Optimization (T-GRPO) method is proposed to achieve unified policy gradient optimization in both discrete and continuous trajectory spaces for MAIT training. Extensive experimental results validate the feasibility and effectiveness of the proposed ARMAIT framework.
title Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks
topic Information Theory
Signal Processing
url https://arxiv.org/abs/2508.16379