Advanced Computational Models and Algorithms for AI-Native Next-Generation Wireless Networks

Dear Colleagues,

The transition toward sixth-generation (6G) and beyond wireless systems is being redefined by artificial intelligence embedded natively across every layer of the network. In AI-native architectures, learning and reasoning are treated not as auxiliary tools, but as first-class design primitives that govern the physical layer, radio resource management, mobility, and end-to-end orchestration. The realisation of this vision requires advanced computational models and algorithms that can operate under stringent latency, reliability, energy, and scalability constraints, as well as under the autonomy of intelligent agents that perceive, decide, and act on behalf of the network.

Original research and high-quality review articles are solicited for this Special Issue on computational intelligence for AI-native next-generation wireless networks. Distributed and agentic AI is of particular interest, in which Belief–Desire–Intention (BDIx) agents and multi-agent systems are made to cooperate in order to manage device-to-device (D2D) and relay communications, massive MIMO, and ultra-reliable low-latency communication (URLLC). A central theme of this Special Issue is the agentic physical channel, in which BDIx agents are used to model, predict, and adapt physical-layer behaviour such as beam selection, channel estimation, link adaptation, and interference control through belief-driven reasoning over noisy channel state information. Contributions that span machine learning, deep learning, reinforcement learning, optimisation, game theory, and explainable and trustworthy AI are welcome, together with reproducible simulation studies and prototypes.

Topics of interest include, but are not limited to, the following:

• Agentic physical-channel modelling, prediction and adaptation using BDIx (Belief–Desire–Intention) agents.
• AI-native physical-layer design, including channel estimation, beamforming, and link adaptation.
• Distributed and multi-agent AI for radio resource management and network orchestration.
• Machine learning and deep learning for massive MIMO and beamspace processing.
• Device-to-device (D2D) and cooperative relay networks for 6G.
• Reinforcement learning and optimisation for ultra-reliable low-latency communication (URLLC).
• Game-theoretic and coalition-based methods for autonomous wireless agents.
• Explainable, trustworthy, and energy-efficient AI for next-generation wireless networks.
• Distributed artificial intelligence (DAI) for wireless network control and coordination.
• Reconfigurable intelligent surfaces (RISs) for AI-native smart radio environments.
• Agentic communication and goal-oriented information exchange between autonomous network agents.
• Mobile network architectures for AI-native 5G and 6G systems.

We look forward to receiving your contributions.

Dr. Iacovos Ioannou
Dr. Michalis Savva
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computation is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• AI-native wireless networks
• 6G and beyond
• agentic artificial intelligence
• BDIx (belief–desire–intention) agents
• agentic physical channel
• distributed artificial intelligence
• machine learning for wireless communications
• massive MIMO
• device-to-device and relay networks
• ultra-reliable low-latency communication (URLLC)