Agentic AI for Embodied-enhanced Beam Prediction in Low-Altitude Economy Networks

Min Hao; Zhizhuo Li; Zirui Zhang; Maoqiang Wu; Han Zhang; Rong Yu

cs.NIMar 12, 2026

Agentic AI for Embodied-enhanced Beam Prediction in Low-Altitude Economy Networks

Authors: Min Hao, Zhizhuo Li, Zirui Zhang, Maoqiang Wu, Han Zhang, Rong Yu

Organizations: School of Electronic Science and Engineering, South China Normal University, Foshan, China · School of Intelligent Engineering, Shaoguan university, Shaoguan, China · School of Automation, Guangdong University of Technology, Guangzhou, China

Abstract

Millimeter-wave or terahertz communications can meet demands of low-altitude economy networks for high-throughput sensing and real-time decision making. However, high-frequency characteristics of wireless channels result in severe propagation loss and strong beam directivity, which make beam prediction challenging in highly mobile uncrewed aerial vehicles (UAV) scenarios. In this paper, we employ agentic AI to enable the transformation of mmWave base stations toward embodied intelligence. We innovatively design a multi-agent collaborative reasoning architecture for UAV-to-ground mmWave communications and propose a hybrid beam prediction model system based on bimodal data. The multi-agent architecture is designed to overcome the limited context window and weak controllability of large language model (LLM)-based reasoning by decomposing beam prediction into task analysis, solution planning, and completeness assessment. To align with the agentic reasoning process, a hybrid beam prediction model system is developed to process multimodal UAV data, including numeric mobility information and visual observations. The proposed hybrid model system integrates Mamba-based temporal modelling, convolutional visual encoding, and cross-attention-based multimodal fusion, and dynamically switches data-flow strategies under multi-agent guidance. Extensive simulations on a real UAV mmWave communication dataset demonstrate that proposed architecture and system achieve high prediction accuracy and robustness under diverse data conditions, with maximum top-1 accuracy reaching 96.57%.

Figures & tables

Fig. 1: UAV-to-ground mmWave beam prediction scenarios and reasoning architecture. Part A illustrates the beam prediction scenario, which includes a mmWave base station equipped with high-definition cameras and UAVs equipped with beam transceivers. Part B presents the architecture and workflow of joint reasoning and beam prediction through the cooperation of the multi-agent and the hybrid model. Inter-agent interactions and reasoning are carried out sequentially following the numbered steps.

Fig. 2: Components and Workflow of Hybrid Beam Prediction Model System. Numeric and image data of UAVs sensed by mmWave base station are processed by encoders for feature extraction and then passed to a decoder to obtain beam prediction results. Specific data-flow switching strategies and encoder parameters are obtained through multi-agent interactive reasoning.

Fig. 3: Performance of TAA in format accuracy and parameter accuracy.

Fig. 4: Relationship between SPA reasoning iterations and reasoning results.

Fig. 5: Performance of CAA in format accuracy and parameter accuracy.

Fig. 6: Impact of training data proportion on beam prediction accuracy.

Fig. 7: Confusion matrices under different prediction scenarios.

Software / Library	Version
Python	3.9
PyTorch	$\geq$ 2.0.0
TorchVision	$\geq$ 0.15.0
Mamba-SSM	$\geq$ 1.2.0
NumPy	$\geq$ 1.23
Pandas	$\geq$ 1.5

TABLE I: Software Environment and Version Requirements

Numeric Encoder Layer=1, Image Encoder Layer=1, Cross-Attention Head=1
Mode	Loss	top-1	top-2	top-3	top-5	Average per-frame inference latency (ms)
Numeric Mode	0.7280	0.7600	0.9212	0.9634	0.9893	0.100
Image Mode	0.5081	0.8152	0.9534	0.9804	0.9926	0.492
Multi Mode	0.2979	0.8874	0.9787	0.9925	0.9980	0.550
Numeric Encoder Layer=2, Image Encoder Layer=2, Cross-Attention Head=2
Mode	Loss	top-1	top-2	top-3	top-5	Average per-frame inference latency (ms)

TABLE II: Performance Comparison under Different Encoder Configurations

Explore similar work

Enwar 3.0: An Agentic Multi-Modal LLM Orchestrator for Situation-Aware Beamforming, Blockage Prediction, and Handover Management
May 4, 2026Ahmad M. Nazar, Abdulkadir Celik, Asmaa Abdallah +3Adaptive Model Routing Wireless Communications
Department of Electrical and Computer Engineering, Iowa State University (ISU), Ames, IA, 50014, USA · Gladiolus Technological Institute, USA · School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. +2
Low-Altitude Channel Multipath Prediction via Panoramic Perception and Vision-Language Model
Jul 24, 2026Zihang Zeng, Shu Sun, Meixia Tao +3Wireless Communications Radio Propagation Modeling
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks
Sep 17, 2026Nguyen Duc Minh Quang, Chang Liu, Shuangyang Li +1LLM-Guided RL Wireless Communications
School of Computing, Engineering, and Mathematical Sciences, La Trobe University, Melbourne, VIC, Australia · Chair of Communications and Information Theory, Technical University of Berlin, 10623 Berlin, Germany · School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia

May 4, 2026J/K move · Enter open · S save

Enwar 3.0: An Agentic Multi-Modal LLM Orchestrator for Situation-Aware Beamforming, Blockage Prediction, and Handover Management

Ahmad M. Nazar, Abdulkadir Celik, Asmaa Abdallah, Mohamed Y. Selim+2

Department of Electrical and Computer Engineering, Iowa State University (ISU), Ames, IA, 50014, USA · Gladiolus Technological Institute, USA · School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K.+2

Adaptive Model Routing Wireless Communications V2X Communication Multimodal Agents

Open paper AskPDF arXiv

Maintaining robust millimeter-wave (mmWave) connectivity in vehicular networks requires real-time adaptation to environmental dynamics, sensor degradation, and link variability. This paper presents Enwar 3.0, an environment-aware reasoning framework that unifies multi-modal sensing, agentic large language models (LLMs), and context-driven model selection for predictive beamforming, blockage detection, and handover management. Building upon prior iterations of Enwar, the proposed architecture integrates a classifier-driven assessment of sensor health with a primed LLM that orchestrates multiple specialized agents through structured, task-aware prompting. A novel synthetic degradation pipeline enables the training of a sensor degradation classifier that detects real-time impairments across camera, radar, LiDAR, and GPS inputs, achieving over 99% accuracy. The LLM, trained via chain-of-thought (CoT) priming and human-in-the-loop feedback, coordinates agent calls for beam selection, blockage forecasting, and environment perception while dynamically loading sensor-specific models based on environmental context. Extensive evaluations across 15 sensor combinations demonstrate that Enwar 3.0 delivers state-of-the-art performance in both predictive accuracy and interpretability, with beam selection accuracy exceeding 88%, blockage F1-scores surpassing 98%, and reasoning correctness reaching 87% on complex decision prompts. This work establishes a scalable foundation for LLM-integrated wireless systems that reason, perceive, and adapt in real-time.

Abstract

Explore similar work

Enwar 3.0: An Agentic Multi-Modal LLM Orchestrator for Situation-Aware Beamforming, Blockage Prediction, and Handover Management

Low-Altitude Channel Multipath Prediction via Panoramic Perception and Vision-Language Model

Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks