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

May 4, 2026

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

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.

Ahmad M. Nazar, Abdulkadir Celik, Asmaa Abdallah +3

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

Ask PDF

Jul 24, 2026

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

Unmanned aerial vehicle (UAV) communication is expected to support a wide range of low-altitude applications in 6G mobile networks. However, traditional statistical channel models provide limited accuracy in specific environments, while deterministic methods such as ray tracing usually rely on accurate three-dimensional environment models and involve high computational complexity. Existing multimodal channel prediction approaches mainly focus on large-scale metrics such as path loss, and remain insufficient for modeling small-scale parameters. To address these limitations, this paper proposes PanoLAMP, a Panoramic perception and vision-language model-based Low-Altitude Multipath Prediction framework. It adopts a pretrained vision-language model as the backbone and captures the propagation environment features through panoramic RGB-D observations collected at both the transmitter and receiver to predict the delay, power, azimuth angle, and zenith angle offset relative to the line-of-sight path. Experiments are conducted on a synthetic dataset containing 18,949 UAV-vehicle links across seven UAV altitudes. Experimental results show that the proposed method consistently outperforms representative baselines in both multipath parameters and statistical metrics, and demonstrates stronger generalization across different flight heights.

Zihang Zeng, Shu Sun, Meixia Tao +3

School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Wireless Communications Radio Propagation Modeling

Ask PDF

Sep 17, 2026

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

Low-altitude wireless networks (LAWNs) are emerging as a key infrastructure for heterogeneous unmanned aerial systems that support concurrent services within a shared three-dimensional airspace. Their coexistence creates strong coupling among mobility, connectivity, and shared network resources, while heterogeneous services impose distinct and time-varying requirements. These interactions naturally form a dynamic non-cooperative game in which both operating conditions and coordination objectives evolve over time. Conventional optimization and learning-based controllers typically rely on predefined objectives, limiting their ability to adapt autonomously to changing service requirements and resource priorities. To address this challenge, we propose a hierarchical hybrid large language model (LLM)- multi-agent reinforcement learning (MARL) architecture organized as a dual-loop structure. Specifically, an outer adaptation loop employs LLM-assisted game orchestration to interpret service requirements and operator intent, and reconfigure objectives and resource priorities, while an inner loop executes decentralized, parameter-conditioned MARL policies under the configured game. A logistics-monitoring case study illustrates how the proposed framework facilitates coordinated coexistence among heterogeneous services, adapting to evolving operating conditions without retraining the underlying MARL policies. Finally, we discuss key challenges and research directions toward scalable, trustworthy, and adaptive agentic LAWNs.

Nguyen Duc Minh Quang, Chang Liu, Shuangyang Li +1

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

LLM-Guided RL Wireless Communications Wireless Resource Allocation Agentic AI Heterogeneous MARL

Ask PDF