Knowledge discovered from telecom data can facilitate proactive understanding of network dynamics and user behaviors, which in turn empowers service providers to optimize cellular traffic scheduling and resource allocation. Nevertheless, the telecom industry still heavily relies on manual expert intervention. Existing studies have been focused on exhaustively explore the spatial-temporal correlations. However, they often overlook the underlying characteristics of cellular traffic, which are shaped by the sporadic and bursty nature of telecom services. Additionally, concept drift creates substantial obstacles to maintaining satisfactory accuracy in continuous cellular forecasting tasks. To resolve these problems, we put forward an online cellular traffic prediction method grounded in Multi-Grained Spatial-Temporal feature Complementarity (MGSTC). The proposed method is devised to achieve high-precision predictions in practical continuous forecasting scenarios. Concretely, MGSTC segments historical data into chunks and employs the coarse-grained temporal attention to offer a trend reference for the prediction horizon. Subsequently, fine-grained spatial attention is utilized to capture detailed correlations among network elements, which enables localized refinement of the established trend. The complementarity of these multi-grained spatial-temporal features facilitates the efficient transmission of valuable information. To accommodate continuous forecasting needs, we implement an online learning strategy that can detect concept drift in real-time and promptly switch to the appropriate parameter update stage. Experiments carried out on four real-world datasets demonstrate that MGSTC outperforms eleven state-of-the-art baselines consistently.

Unmanned Aerial Vehicles (UAVs) have made significant advancements in communication stability and security through techniques such as frequency hopping, signal spreading, and adaptive interference suppression. However, challenges remain in modeling spectrum competition, integrating expert knowledge, and predicting opponent behavior. To address these issues, we propose UAV-FPG (Unmanned Aerial Vehicle - Frequency Point Game), a game-theoretic environment model that simulates the dynamic interaction between interference and anti-interference strategies of opponent and ally UAVs in communication frequency bands. The model incorporates a prior expert knowledge base to optimize frequency selection and employs large language models for path planning, simulating a "strong adversary". Experimental results highlight the effectiveness of integrating the expert knowledge base and the large language model, with the latter significantly improving path planning in dynamic scenarios through iterative interactions, outperforming fixed-path strategies. UAV-FPG provides a robust platform for advancing anti-jamming strategies and intelligent decision-making in UAV communication systems.

--Accurate and adaptive network throughput prediction is essential for latency-sensitive and bandwidth-intensive applications in 5G and emerging 6G networks. However, most existing methods rely on centralized training with uniformly collected data, limiting their applicability in heterogeneous mobile environments with non-IID data distributions. This paper presents the first comprehensive benchmarking of federated learning (FL) strategies for throughput prediction in realistic 5G edge scenarios. We evaluate three aggregation algorithms - F edAvg, F edProx, and F edBN-across four time-series architectures: LSTM, CNN, CNN+LSTM, and Transformer, using five diverse real-world datasets. We systematically analyze the effects of client heterogeneity, cohort size, and history window length on prediction performance. Our results reveal key trade-offs among model complexities, convergence rates, and generalization. It is found that F edBN consistently delivers robust performance under non-IID conditions. LSTM is, therefore, found to achieve a favorable balance between accuracy, rounds, and temporal footprint. T o validate the end-to-end applicability of the framework, we have integrated our FL-based predictors into a live adaptive streaming pipeline. It is seen that F edBN-based LSTM and Transformer models improve mean QoE scores by 11.7% and 11.4%, respectively, over F edAvg, while also reducing the variance. These findings offer actionable insights for building scalable, privacy-preserving, and edge-aware throughput prediction systems in next-generation wireless networks. HE increasing demand for high-bandwidth, low-latency applications in next-generation wireless networks, such as 5G and the emerging 6G, has made accurate and robust network throughput prediction indispensable for sustaining performance under dynamic and resource-constrained network conditions. Dutta and B.Palit are with the Department of Electronics and Communication Engineering, National Institute of Technology Rourkela, India - 769008.

In this work, we address the problem of training Reinforcement Learning (RL) agents over communication networks. The RL paradigm requires the agent to instantaneously perceive the state evolution to infer the effects of its actions on the environment. This is impossible if the agent receives state updates over lossy or delayed wireless systems and thus operates with partial and intermittent information. In recent years, numerous frameworks have been proposed to manage RL with imperfect feedback; however, they often offer specific solutions with a substantial computational burden. To address these limits, we propose a novel architecture, named Homomorphic Robust Remote Reinforcement Learning (HR3L), that enables the training of remote RL agents exchanging observations across a non-ideal wireless channel. HR3L considers two units: the transmitter, which encodes meaningful representations of the environment, and the receiver, which decodes these messages and performs actions to maximize a reward signal. Importantly, HR3L does not require the exchange of gradient information across the wireless channel, allowing for quicker training and a lower communication overhead than state-of-the-art solutions. Experimental results demonstrate that HR3L significantly outperforms baseline methods in terms of sample efficiency and adapts to different communication scenarios, including packet losses, delayed transmissions, and capacity limitations.

As multi-agent systems (MAS) become increasingly prevalent in autonomous systems, distributed control, and edge intelligence, efficient communication under resource constraints has emerged as a critical challenge. Traditional communication paradigms often emphasize message fidelity or bandwidth optimization, overlooking the task relevance of the exchanged information. In contrast, goal-oriented communication prioritizes the importance of information with respect to the agents' shared objectives. This review provides a comprehensive survey of goal-oriented communication in MAS, bridging perspectives from information theory, communication theory, and machine learning. We examine foundational concepts alongside learning-based approaches and emergent protocols. Special attention is given to coordination under communication constraints, as well as applications in domains such as swarm robotics, federated learning, and edge computing. The paper concludes with a discussion of open challenges and future research directions at the intersection of communication theory, machine learning, and multi-agent decision making.

With wireless devices increasingly forming a unified smart network for seamless, user-friendly operations, random access (RA) medium access control (MAC) design is considered a key solution for handling unpredictable data traffic from multiple terminals. However, it remains challenging to design an effective RA-based MAC protocol to minimize collisions and ensure transmission fairness across the devices. While existing multi-agent reinforcement learning (MARL) approaches with centralized training and decentralized execution (CTDE) have been proposed to optimize RA performance, their reliance on centralized training and the significant overhead required for information collection can make real-world applications unrealistic. In this work, we adopt a fully decentralized MARL architecture, where policy learning does not rely on centralized tasks but leverages consensus-based information exchanges across devices. We design our MARL algorithm over an actor-critic (AC) network and propose exchanging only local rewards to minimize communication overhead. Furthermore, we provide a theoretical proof of global convergence for our approach. Numerical experiments show that our proposed MARL algorithm can significantly improve RA network performance compared to other baselines.

The contents of this paper may change at any time without notice. Abstract --With the emergence of 6G, mobile networks are becoming increasingly heterogeneous and dynamic, necessitating advanced automation for efficient management. Intent-Driven Networks (IDNs) address this by translating high-level intents into optimization policies. Large Language Models (LLMs) can enhance this process by understanding complex human instructions to enable adaptive, intelligent automation. Given the rapid advancements in Generative AI (GenAI), a comprehensive survey of LLM-based IDN architectures in disaggregated Radio Access Network (RAN) environments is both timely and critical. This article provides such a survey, along with a case study on a hierarchical learning-enabled IDN architecture that integrates GenAI across three key stages: intent processing, intent validation, and intent execution. Unlike most existing approaches that apply GenAI in the form of LLMs for intent processing only, we propose a hierarchical framework that introduces GenAI across all three stages of IDN. T o demonstrate the effectiveness of the proposed IDN management architecture, we present a case study based on the latest GenAI architecture named Mamba. The case study shows how the proposed GenAI-driven architecture enhances network performance through intelligent automation, surpassing the performance of the conventional IDN architectures. Sixth-Generation (6G) networks are anticipated to support a diverse set of user requirements and have more complex deployments [1].

The advent of 6G networks opens new possibilities for connected infotainment services in vehicular environments. However, traditional Radio Resource Management (RRM) techniques struggle with the increasing volume and complexity of data such as Channel Quality Indicators (CQI) from autonomous vehicles. To address this, we propose SCAR (State-Space Compression for AI-Driven Resource Management), an Edge AI-assisted framework that optimizes scheduling and fairness in vehicular infotainment. SCAR employs ML-based compression techniques (e.g., clustering and RBF networks) to reduce CQI data size while preserving essential features. These compressed states are used to train 6G-enabled Reinforcement Learning policies that maximize throughput while meeting fairness objectives defined by the NGMN. Simulations show that SCAR increases time in feasible scheduling regions by 14\% and reduces unfair scheduling time by 15\% compared to RL baselines without CQI compression. Furthermore, Simulated Annealing with Stochastic Tunneling (SAST)-based clustering reduces CQI clustering distortion by 10\%, confirming its efficiency. These results demonstrate SCAR's scalability and fairness benefits for dynamic vehicular networks.

We introduce a low-latency telecom AI voice agent pipeline for real-time, interactive telecommunications use, enabling advanced voice AI for call center automation, intelligent IVR (Interactive Voice Response), and AI-driven customer support. The solution is built for telecom, combining four specialized models by NetoAI: TSLAM, a 4-bit quantized Telecom-Specific Large Language Model (LLM); T-VEC, a Telecom-Specific Embedding Model; TTE, a Telecom-Specific Automatic Speech Recognition (ASR) model; and T-Synth, a Telecom-Specific Text-to-Speech (TTS) model. These models enable highly responsive, domain-adapted voice AI agents supporting knowledge-grounded spoken interactions with low latency. The pipeline integrates streaming ASR (TTE), conversational intelligence (TSLAM), retrieval augmented generation (RAG) over telecom documents, and real-time TTS (T-Synth), setting a new benchmark for telecom voice assistants. To evaluate the system, we built a dataset of 500 human-recorded telecom questions from RFCs, simulating real telecom agent queries. This framework allows analysis of latency, domain relevance, and real-time performance across the stack. Results show that TSLAM, TTE, and T-Synth deliver real-time factors (RTF) below 1.0, supporting enterprise, low-latency telecom deployments. These AI agents -- powered by TSLAM, TTE, and T-Synth -- provide a foundation for next-generation telecom AI, enabling automated customer support, diagnostics, and more.

SoftBank Group swung to a quarterly profit, riding on gains from its bets on Nvidia and startups in a boon for founder Masayoshi Son's bets on artificial intelligence technologies. A recovery at SoftBank's signature Vision Fund and the sale of assets such as its T-Mobile U.S. holdings are helping Son double down on bets geared to help him capitalize on booming investment in AI hardware. SoftBank, which had sold 4.8 billion worth of its stake in the U.S. telecom company in June, on Thursday revealed the sale of another 3 billion of the U.S. carrier's stock. The Tokyo-based company reported net income of 421.82 billion ( 2.9 billion) in its fiscal first quarter, more than double the average of analyst estimates. The Vision Fund logged a 451.39 billion profit, helped by a recovery in tech valuations and gains on holdings such as Coupang, Auto1 Group SE, Symbotic and Swiggy.