Ping Yang

Multi-tier aerial communication networks (MACNs), integrating satellites, high-altitude platforms, and unmanned aerial vehicles, are emerging as a cornerstone of next-generation global connectivity. Their promise of resilient and ubiquitous coverage, however, is hindered by highly dynamic topologies, severe energy and computational constraints, environment-sensitive channels, diverse quality-of-service requirements, and limited real-world validation. Artificial intelligence (AI) has increasingly been explored as a flexible framework to address these challenges, enabling adaptive routing, distributed computing and task offloading, handover management, intelligent resource allocation, and large-scale network optimization. This survey provides a comprehensive and structured review of methods for MACNs, with particular emphasis on AI-driven solutions and their relationship to classical and hybrid alternatives. We critically evaluate representative approaches in terms of scalability, efficiency, data demands, and practical deployability, and identify emerging trends such as graph neural networks with reinforcement learning for dynamic routing, predictive learning for mobility management, and federated learning for distributed computation. Persistent challenges remain in lightweight edge intelligence, real-world testbeds, reproducible benchmarking, and simulation-to-deployment transfer. To address these issues, we offer a research roadmap emphasizing compressible and interpretable models, standardized benchmarks, realistic validation, and hybrid designs that balance adaptability with computational and energy overhead. Finally, we identify open challenges and future research directions, offering insights into the design of AI-driven MACNs that are efficient, scalable, and adaptive to evolving network and service demands.

Fluid antenna systems (FASs) introduce antenna position as a reconfigurable spatial degree of freedom (DoF), enabling adaptive interaction with the propagation environment and efficient utilization of spatial resources. This survey provides a comprehensive review of DoF exploitation in FAS-enabled wireless communications, covering reliability enhancement, high-throughput transmission, and multi-access connectivity. Beyond these core functionalities, FASs also support a range of multifunctional capabilities, such as integrated sensing and communication (ISAC), simultaneous wireless information and power transfer (SWIPT), secure and covert transmission, and artificial intelligence (AI)-driven configuration. As a concrete example of this vision, we present a novel fluid antenna-enabled quadrature index modulation (FA-QIM) framework to illustrate how this spatial DoF can be architected to enable high-rate and robust ISAC. Collectively, these investigations illustrate the evolution of FAS from a diversity-enhancing technique to a core enabler of multifunctional networks, bridging theoretical DoF analysis with system-level design considerations. It concludes by outlining open challenges and potential avenues toward intelligent, multi-functional FAS architectures for next-generation networks.

The performance benefits of invoking transmit antenna selection (TAS) for phase-shifter-aided spatial multiplexing (PSSM) systems are investigated. In contrast to conventional spatial multiplexing systems employing TAS, the proposed TAS for PSSM (TAS-PSSM) system is targeted to jointly determine both the optimal subset of active antennas and the optimal connectivity pattern (CP) between the phase shifters and the transmit antennas. The combination of the antenna subset and CP is optimized by minimizing the conditional pairwise error probability (PEP) for each channel realization. Specifically, this framework is further decomposed into two components. The first component focuses exclusively on the method of the phase-shifter connectivity pattern selection (PSCPS), where the Euclidean distance (ED)-based PSCPS (ED-PSCPS) approach is adopted as a benchmark, upon which two lower complexity alternatives are developed, including radio frequency chain-based PSCPS (RF-PSCPS) and norm-based PSCPS (N-PSCPS). The second component addresses reduced complexity solutions to optimize the active antenna selection (AAS), including Rayleigh–Ritz-based AAS (RR-AAS) and norm-based AAS (N-AAS) schemes. Finally, our simulation results demonstrate that the proposed simplified PSCPS schemes achieve near-identical performance to that of the original ED-PSCPS while significantly reducing computational complexity. Moreover, RR-AAS and N-AAS algorithms strike a compelling tradeoff between the bit error rate (BER) performance and the associated computational complexity when compared to their AAS-free counterpart.

The rapid expansion of the low-altitude economy (LAE) necessitates robust and intelligent integrated sensing and communication (ISAC) systems. These systems are critical for managing dense airspace, ensuring safe navigation of drones and electric vertical take-off and landing (eVTOL), and delivering seamless data services. This paper explores the transformative potential of large language models (LLMs) in advancing ISAC technologies for LAE applications. LLMs, with their profound capabilities in contextual understanding, multi-modal data fusion, and probabilistic reasoning, can be leveraged to interpret complex sensing data, optimize communication resources, and facilitate intelligent decision-making in dynamic environments. As a concrete example, we introduce an LLM-based multi-scale three-dimensional (3-D) localization framework. This algorithm utilizes an LLM as a cognitive engine to integrate and analyze the acquired data streams and is capable of providing multi-scale positioning for unmanned aerial vehicles (UAVs). Moreover, we outline a number of key technical challenges as well as potential solutions associated with LLM-aided ISAC for LAE.

Emerging low-altitude economy networks require agile and privacy-preserving resource control under dynamic agent mobility and limited infrastructure support. To address these challenges, we propose a vision-aided integrated sensing and communication framework for intelligent aerial agent-assisted access systems, where onboard masked De-Diffusion models extract compact semantic tokens, including agent type, activity class, and heading orientation, while explicitly suppressing sensitive visual content. These tokens are fused with mmWave radar measurements to construct a semantic risk heatmap reflecting motion density, occlusion, and scene complexity, which guides access technology selection and resource scheduling. We formulate a multi-objective optimization problem to jointly maximize weighted energy and perception efficiency via radio access technology (RAT) assignment, power control, and beamforming, subject to agent-specific QoS constraints. To solve it, we develop De-Diffusion-driven vision-aided risk-aware resource optimization algorithm (DeDiff-VARARO), a novel two-stage cross-modal control algorithm: the first stage reconstructs visual scenes from tokens via De-Diffusion model for semantic parsing, while the second stage employs a deep deterministic policy gradient-based policy to adapt RAT selection, power control, and beam assignment based on fused radar-visual states. Simulation results show that DeDiff-VARARO consistently outperforms baselines in reward convergence, link robustness, and semantic fidelity, achieving within 4% of the performance of a raw-image upper bound while preserving user privacy and scalability in dense environments.

With the rapid growth of intelligent services, communication targets are shifting from humans to artificial intelligent (AI) agents, which require new paradigms to enable real-time perception, decision-making, and collaboration. Semantic communication, which conveys task-relevant meaning rather than raw data, offers a promising solution. However, its practical deployment remains constrained by dynamic environments and limited resources. To address these issues, this article proposes a semantic-driven AI agent communication framework and develops three enabling techniques. First, semantic adaptation transmission applies fine-tuning with real or generative samples to efficiently adapt models to varying environments. Second, semantic lightweight transmission incorporates pruning, quantization, and perception-aware sampling to reduce model complexity and alleviate computational burden on edge agents. Third, semantic self-evolution control employs distributed hierarchical decision-making to optimize multi-dimensional resources, enabling robust multi-agent collaboration in dynamic environments. Simulation results show that the proposed solutions achieve faster convergence and stronger robustness, while the proposed distributed hierarchical optimization method significantly outperforms conventional decision-making schemes, highlighting its potential for AI agent communication networks.

The low-altitude economy (LAE), an emerging economic paradigm encompassing various flight activities in low-altitude airspace, has attracted widespread attention from academia and industry due to its appealing economic and social benefits. In this paper, we investigate the design of integrated sensing and communication (ISAC) waveforms for LAE applications. Specifically, we propose an adaptive ISAC waveform, which integrates the maximum distance separable (MDS) code and index modulation (IM) into the orthogonal frequency division multiplexing (OFDM) waveform, namely A-MDS-OFDM-IM. This design combines the hybrid benefits of MDS code, IM, and OFDM techniques, i.e., the error detection capability of MDS code, the high spectral efficiency (SE) of IM, and the high sensing resolution of OFDM, thereby enabling robust communication and sensing. A comprehensive performance analysis of A-MDS-OFDM-IM is provided, including its bit error rate (BER), peak-to-sidelobe level (PSL), and peak-to-average power ratio (PAPR). Moreover, to address the high PAPR issue of A-MDS-OFDM-IM, we develop an adaptive design criterion based on the alternating direction method of multipliers (ADMM), which is capable of jointly optimizing the communication, sensing, and PAPR performance of the proposed system. Simulation results demonstrate that the proposed waveform achieves better BER performance than conventional OFDM-based waveforms under a non-ideal high power amplifier (HPA), owing to its low-PAPR characteristic. Additionally, the proposed waveform ensures robust sensing with satisfactory PSL performance, making it a promising ISAC waveform for LAE applications.

Near-field communications (NFC) are rapidly evolving as a pivotal enabler for 6G technologies, driven by extremely-large multiple-input multiple-output (XL-MIMO), reconfigurable intelligent surface (RIS), and high-frequency bands. This survey comprehensively reviews emerging modulation paradigms that exploit the unique properties of spherical wavefronts in the near-field region. Specifically, we sketch the potential requirements and present an overview of the latest research on the promising modulation techniques for NFC, e.g., the advanced index modulation, beamforming-centric modulation, polarization modulation, delay alignment modulation, as well as direction modulation, which have recently attracted considerable attention. Responding to the trend toward multifunctional NFC modulation, we propose a novel framework exploiting distinctive modulation schemes, flexible waveform design, and near-field degrees of freedom. Moreover, we outline a number of key technical challenges as well as the potential solutions associated with modulation designs for NFC.