The IEEE Transactions on Cognitive Communications and Networking (TCCN) is committed to timely publishing of high-quality manuscripts that advance the state-of-the-art of cognitive communications and networking research. The focus of the Transactions will be on “cognitive” behaviors in all aspects of communications and network control, from the PHY functions (including hardware) through the applications (including architecture), and in all kinds of communication networks and systems regardless of type of traffic, transmission media, operating environment, or capabilities of communicating devices. IEEE TCCN will welcome papers dealing with the design, analysis, evaluation, experimentation and testing of cognitive communications and network systems. Inter-disciplinary approaches are encouraged. Papers that focus on experimental infrastructures or tools for cognitive communications and networking will also be considered, provided that they contain significant original contributions in the communications or networking areas.

Since the term “cognitive” may be interpreted in multiple ways, we define here a cognitive entity as one that is capable of selecting and carrying out actions depending on its own goals and its perception of the world and that may also be capable of learning from experience by interacting with the world. Thus, a cognitive entity means an intelligent entity which possesses the following basic components: perception, learning/reasoning and decision making. Papers that will be considered for publication in the IEEE Transactions on Cognitive Communications and Networking must BOTH explicitly include approaches related to the “intelligent entity” AND provide original contributions on communications or networking.

Topics of interest include (but are not limited to):

    Machine learning and artificial intelligence for communications and networking
    Distributed learning, reasoning and optimization for communications and networking
    Architecture, protocols, cross-layer, and cognition cycle design for intelligent communications and networking
    Information/communications theory and network science for intelligent communications and networking
    Ontologies, languages, and knowledge representation for intelligent communications and networking
    Security and privacy issues in intelligent communications and networking
    Cognitive radio and dynamic spectrum access
    Cognitive technologies supporting software-defined radios, systems and networks
    Emerging services and applications enabled by intelligent communications and networks

Special issues will form an integral part of IEEE TCCN. Guest editorial teams are welcome to propose special issues on new emerging areas in cognitive and intelligent communications and networking. Please contact the Editor-in-Chief if you are interested in submitting a proposal.

Special Issue on Fluid Antenna Systems and Other Reconfigurable Antenna Technologies: From Conventional Designs to AI-Driven Networks
Día de Entrega: 2025-10-30

Next-generation wireless communication systems, especially sixth-generation (6G) networks, are evolving from traditional static hardware designs toward intelligent, adaptive, and self-organizing architectures. These networks demand seamless spectrum awareness, dynamic interference suppression, and efficient resource allocation to support massive connectivity, ultra-reliable low-latency communications (URLLC), and high energy efficiency. As a frontier breakthrough, fluid antenna systems (FAS) enable real-time, software-controlled reconfiguration of antenna position, shape, and radiation pattern. This unprecedented flexibility transforms conventional transceiver design by introducing new physical-layer degrees of freedom that boost spectrum utilization, network capacity, and link performance through dynamic reconfiguration.

FAS operates alongside other cutting-edge wireless technologies, such as reconfigurable intelligent surfaces (RIS), non-orthogonal multiple access (NOMA), to form a cohesive next-generation ecosystem. Recent innovations like fluid antenna multiple access (FAMA), compact ultra-massive antenna arrays (CUMA), and various metasurface-based reconfigurable antennas demonstrate how these architectures can enhance spectrum efficiency, mitigate interference, and increase spatial diversity without simply scaling up RF chains or relying on static MIMO arrays.

Integrating artificial intelligence (AI), machine learning (ML), and large language models (LLMs) with FAS drives a paradigm shift in algorithm design, from traditional convex and heuristic methods for beamforming optimization, MMSE/Kalman-filter channel estimation, rule-based resource partitioning, and triangulation-based localization, to deep reinforcement learning for dynamic antenna configuration, neural-network channel prediction, graph-based resource distribution, and DL-enabled high-precision positioning. AI/ML-driven algorithms can jointly optimize antenna selection, spectrum scheduling, traffic prediction, resource allocation, and user localization to maximize throughput, reliability, and energy efficiency under diverse channel and load conditions, while dramatically reducing decision latency and computational overhead. LLM-based orchestration engines further process large-scale telemetry to generate context-aware control policies and automate complex FAS management workflows, enabling truly autonomous, data-driven wireless systems that adapt proactively to changing environments and simplify operational complexity.

Moreover, FAS is central to integrated sensing and computing (ISAC) methodologies, allowing wireless systems to combine communication, sensing, AI-driven analytics, and on-device computation within a unified framework. In increasingly complex scenarios, secure, resilient, and intelligent links are vital. By leveraging both traditional optimization algorithms (e.g., convex beamforming, Kalman-filter channel estimation) and AI-driven approaches (e.g., deep reinforcement learning for beam control, federated learning for distributed resource allocation), FAS enables privacy-aware beamforming, secure dynamic networking, and adaptive interference-resistant transmission. Advanced channel estimation and prediction techniques—ranging from classical MMSE and Kalman filtering to ML- and LLM-based inference—refine sensing accuracy, support real-time channel analysis, and drive seamless network adaptation. Furthermore, algorithmic innovations in resource distribution, network performance analysis, and high-precision user localization, transitioning from heuristic and convex-solver methods to graph neural networks and deep learning, empower FAS-enabled systems to perform end-to-end optimization, traffic prediction, and centimeter-level positioning.

Industry momentum behind FAS is accelerating, as seen in plasma-based reconfigurable antennas for mmWave bands, flexible-position MIMO prototypes for edge computing, and AI-driven RAN orchestration solutions powered by deep neural networks and LLM-based policy engines. These advances underscore the commercial potential of FAS and highlight the need for cross-industry collaboration among antenna designers, AI researchers, network operators, and standards bodies. Future research must bridge traditional communication-theoretic algorithms with cutting-edge AI/ML frameworks for channel modeling, performance analysis, optimization, resource distribution, and localization. By integrating supervised learning for channel estimation, reinforcement learning for dynamic antenna configuration, and LLM-driven orchestration with established signal processing and information-theoretic methods, next-generation 6G networks can realize truly autonomous, self-optimizing wireless systems.

In response to these advancements, IEEE Transactions on Cognitive Communications and Networking (TCCN) presents this special issue to provide a dedicated platform for exploring state-of-the-art developments in FAS and reconfigurable antenna technologies for cognitive wireless networks. This issue seeks novel contributions addressing the design, optimization, and integration of FAS in next-generation cognitive communication frameworks.

We invite original research articles, surveys, and case studies that explore theoretical foundations, algorithmic innovations, system implementations, and performance evaluations of FAS and related reconfigurable antenna technologies in cognitive wireless networks. Topics of interest include, but are not limited to:

Topics of Interest:

    Advanced transceiver design with FAS – from conventional analog/digital beamforming to AI-driven adaptive beamforming
    Integrated sensing, communication, and computing (ISCC) in FAS-enhanced networks – from separate radar/comm modules to unified AI-augmented ISCC frameworks
    Optimization of FAS-enabled systems – from heuristic resource scheduling to AI/LLM-driven holistic network orchestration
    Security and privacy for FAS-based communication – from static encryption and beamforming to AI-based threat detection and reconfigurable-secure transmissions
    Channel estimation and spectrum sensing for FAS – from MMSE/Kalman filters and energy detection to ML/LLM-powered predictive inference
    Reconfigurable intelligent surfaces (RIS) in FAS-integrated networks – from fixed phase-shift designs to AI-controlled dynamic RIS–FAS synergy
    Multiple access with FAS – from traditional NOMA/TDMA schemes to AI-optimized NGMA and Fluid Antenna Multiple Access (FAMA)
    Energy-efficient FAS implementations – from hardware-centric power reduction to AI-driven energy-aware reconfiguration
    Interoperability between FAS and conventional MIMO – from isolated deployments to AI-coordinated hybrid architectures
    Massive IoT connectivity with FAS – from static endpoint provisioning to AI-managed, FAS-enabled massive IoT networks
    Standardization efforts for FAS – from legacy RF guidelines to AI-informed, cross-industry frameworks for reconfigurable antennas
    Load balancing and resource allocation in FAS environments – from fixed scheduling to AI-based dynamic optimization
    FAS-driven holographic surfaces – from fixed holographic antenna arrays to AI-empowered, reconfigurable holographic surfaces
    Experimental and real-world testbeds – from prototype demonstrations to AI-monitored, large-scale FAS deployments
    Localization with FAS – from triangulation and fingerprinting to AI-enhanced, high-precision positioning algorithms
    Stacked intelligent metasurfaces for FAS – from single-layer metasurfaces to AI-optimized, multi-layer intelligent metasurface stacks
    FAS-enabled satellite and non-terrestrial networks – from static satellite antennas to AI-driven, reconfigurable FAS for space and aerial links

Special Issue on Agentic AI for Communications and Networking with Embodied Intelligence
Día de Entrega: 2026-01-01

The exponential growth of connected networking devices, projected to surpass 125 billion by 2030, has created unprecedented demands on modern networking systems. These networking systems are required to handle massive amounts of data traffic, support seamless interactions across disparate devices, and incorporate embodied intelligence for real-time decision making and adaptive control, while addressing the challenges of a decentralized and dynamic environment. To address these challenges, Agentic AI emerges as a transformative paradigm, deploying autonomous agents capable of perceiving their environment, learning from data, and making intelligent decisions independently or collaboratively. Unlike traditional AI techniques, which often struggle with scalability and adaptability, Agentic AI leverages advanced technologies such as Embodied AI, large language models (LLMs), deep reinforcement learning (DRL), and generative AI (GenAI) to enhance network performance, optimize resource allocation, and enable real-time decision-making.

Integrating Agentic AI into communications and networking with Embodied Intelligence, however, presents several critical challenges. These include developing innovative protocols to ensure low-latency and scalable interactions among agents, optimizing resource management across computation, communication, and storage domains, and implementing robust security mechanisms to protect agents from adversarial threats. Additionally, addressing infrastructure constraints such as interference, mobility, and resource availability requires novel cross-layer optimization strategies. Deployment and testing in real-world scenarios are equally vital, necessitating the design of scalable testbeds to validate Agentic AI-driven networking solutions. Given these challenges, this special issue focuses on exploring foundational solutions and operational paradigms to integrate Agentic AI into networking systems effectively. The scope includes but not limited to:

    Foundational Frameworks for Agentic AI in Communications and Networking with Embodied Intelligence
    Standardization of Agentic AI Architectures and Protocols for Communications and Networking with Embodied Intelligence
    Agentic AI for Enhancing the Performance of B5G and 6G Networks
    Dynamic Spectrum Management and Resource Allocation in Embodied Networks
    LLM and GenAI Agents for Semantic Networking and Adaptive Optimization 
    Security and Privacy Mechanisms for Agentic AI Communications and Networking with Embodied Intelligence
    Agentic AI for Embodied-enhanced Sustainable Networking
    Embodied Multi-Agentic AI Coordination Strategies for Communications and Networking
    Embodied Intelligence in Edge Computing and IoT Networking
    Embodied Intelligence for Internet of Agent Networking
    Agentic AI for Embodied-enhanced UAV Networking in Low-Altitude Economies
    Cross-Layer Optimization Frameworks for Agentic AI-enhanced Communications and Networking
    Testbeds and Practical Deployments for Agentic AI in B5G and 6G Networks with Embodied Intelligence

Submission Guidelines

Prospective authors are invited to submit their manuscripts electronically, adhering to the IEEE Transactions on Cognitive Communications and Networking guidelines. Note that the page limit is the same as that of regular papers. Please submit your papers through the online system and be sure to select the special issue or special section name. Manuscripts should not be published or currently submitted for publication elsewhere. Please submit only full papers intended for review, not abstracts, to the ScholarOne portal. If requested, abstracts should be sent by e-mail directly to the Guest Editors.

Important Dates

Manuscript Submission: 1 January 2026
First Review Round: 1 March 2026
Revision Papers Due: 1 April 2026
Acceptance Notification: 1 May 2026
Final Manuscript Due: 15 June 2026
Publication Date: 2026

Guest Editors

Ruichen Zhang
Nanyang Technological University, Singapore

Yonghui Li
University of Sydney, Australia

Ping Wang
York University, Canada

Merouane Debbah
Khalifa University, UAE

Sumei Sun
Agency for Science, Technology, and Research (A*STAR), Singapore