Merouane Debbah

Wneya Yu, Chao Zhang, Li Wang et al.

Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for efficient Large Language Model (LLM) deployment. However, applying them sequentially poses a problem: PTQ often leaves behind random noise that is spread out (across the model's weights) in a way LoRA can't easily fix, meaning that LoRA ends up wasting its limited capacity trying to fix uncorrectable noise instead of improving task performance. In this paper, we propose \textbf{ProjQ}, a novel framework for constraining quantization noise to the low-rank manifold via orthogonal subspace projection. We derive an efficient alternating algorithm that shapes the quantization noise into a low-rank structure, effectively offloading dominant error components to the subsequent adapter while minimizing the residual error in the orthogonal "uncorrectable" subspace. Our theoretical analysis demonstrates that ProjQ preserves strictly greater model plasticity for downstream tasks compared to standard PTQ. Extensive experiments on LLaMA-2, Qwen2.5 and Qwen3 confirm that ProjQ consistently outperforms existing methods in both quantization error compensation and downstream task fine-tuning, achieving up to $2\times$ lower evaluation loss for compensation and matching the performance of standard 4-bit baselines on language modeling tasks with only 3 bits. The code is available on https://github.com/yy9301/ProjQ .

Christina Chaccour, Walid Saad, Merouane Debbah et al.

Semantic communication is viewed as a revolutionary paradigm that can potentially transform how we design and operate wireless communication systems. However, despite a recent surge of research activities in this area, the research landscape remains limited. In this tutorial, we present the first rigorous vision of a scalable end-to-end semantic communication network that is founded on novel concepts from artificial intelligence (AI), causal reasoning, and communication theory. We first discuss how the design of semantic communication networks requires a move from data-driven networks towards knowledge-driven ones. Subsequently, we highlight the necessity of creating semantic representations of data that satisfy the key properties of minimalism, generalizability, and efficiency so as to do more with less. We then explain how those representations can form the basis a so-called semantic language. By using semantic representation and languages, we show that the traditional transmitter and receiver now become a teacher and apprentice. Then, we define the concept of reasoning by investigating the fundamentals of causal representation learning and their role in designing semantic communication networks. We demonstrate that reasoning faculties are majorly characterized by the ability to capture causal and associational relationships in datastreams. For such reasoning-driven networks, we propose novel and essential semantic communication metrics that include new "reasoning capacity" measures that could go beyond Shannon's bound to capture the convergence of computing and communication. Finally, we explain how semantic communications can be scaled to large-scale networks (6G and beyond). In a nutshell, we expect this tutorial to provide a comprehensive reference on how to properly build, analyze, and deploy future semantic communication networks.

Lina Bariah, Qiyang Zhao, Hang Zou et al.

The evolution of generative artificial intelligence (GenAI) constitutes a turning point in reshaping the future of technology in different aspects. Wireless networks in particular, with the blooming of self-evolving networks, represent a rich field for exploiting GenAI and reaping several benefits that can fundamentally change the way how wireless networks are designed and operated nowadays. To be specific, large GenAI models are envisioned to open up a new era of autonomous wireless networks, in which multi-modal GenAI models trained over various Telecom data, can be fine-tuned to perform several downstream tasks, eliminating the need for building and training dedicated AI models for each specific task and paving the way for the realization of artificial general intelligence (AGI)-empowered wireless networks. In this article, we aim to unfold the opportunities that can be reaped from integrating large GenAI models into the Telecom domain. In particular, we first highlight the applications of large GenAI models in future wireless networks, defining potential use-cases and revealing insights on the associated theoretical and practical challenges. Furthermore, we unveil how 6G can open up new opportunities through connecting multiple on-device large GenAI models, and hence, paves the way to the collective intelligence paradigm. Finally, we put a forward-looking vision on how large GenAI models will be the key to realize self-evolving networks.

Nicola Piovesan, David Lopez-Perez, Antonio De Domenico et al.

The energy consumption of the fifth generation(5G) of mobile networks is one of the major concerns of the telecom industry. However, there is not currently an accurate and tractable approach to evaluate 5G base stations (BSs) power consumption. In this article, we propose a novel model for a realistic characterisation of the power consumption of 5G multi-carrier BSs, which builds on a large data collection campaign. At first, we define a machine learning architecture that allows modelling multiple 5G BS products. Then, we exploit the knowledge gathered by this framework to derive a realistic and analytically tractable power consumption model, which can help driving both theoretical analyses as well as feature standardisation, development and optimisation frameworks. Notably, we demonstrate that such model has high precision, and it is able of capturing the benefits of energy saving mechanisms. We believe this analytical model represents a fundamental tool for understanding 5G BSs power consumption, and accurately optimising the network energy efficiency.

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

This paper introduces 6G-Bench, an open benchmark for evaluating semantic communication and network-level reasoning in AI-native 6G networks. 6G-Bench defines a taxonomy of 30 decision-making tasks (T1--T30) extracted from ongoing 6G and AI-agent standardization activities in 3GPP, IETF, ETSI, ITU-T, and the O-RAN Alliance, and organizes them into five standardization-aligned capability categories. Starting from 113,475 scenarios, we generate a balanced pool of 10,000 very-hard multiple-choice questions using task-conditioned prompts that enforce multi-step quantitative reasoning under uncertainty and worst-case regret minimization over multi-turn horizons. After automated filtering and expert human validation, 3,722 questions are retained as a high-confidence evaluation set, while the full pool is released to support training and fine-tuning of 6G-specialized models. Using 6G-Bench, we evaluate 22 foundation models spanning dense and mixture-of-experts architectures, short- and long-context designs (up to 1M tokens), and both open-weight and proprietary systems. Across models, deterministic single-shot accuracy (pass@1) spans a wide range from 0.22 to 0.82, highlighting substantial variation in semantic reasoning capability. Leading models achieve intent and policy reasoning accuracy in the range 0.87--0.89, while selective robustness analysis on reasoning-intensive tasks shows pass@5 values ranging from 0.20 to 0.91. To support open science and reproducibility, we release the 6G-Bench dataset on GitHub: https://github.com/maferrag/6G-Bench

Lina Bariah, Hang Zou, Qiyang Zhao et al.

The recent progress of artificial intelligence (AI) opens up new frontiers in the possibility of automating many tasks involved in Telecom networks design, implementation, and deployment. This has been further pushed forward with the evolution of generative artificial intelligence (AI), including the emergence of large language models (LLMs), which is believed to be the cornerstone toward realizing self-governed, interactive AI agents. Motivated by this, in this paper, we aim to adapt the paradigm of LLMs to the Telecom domain. In particular, we fine-tune several LLMs including BERT, distilled BERT, RoBERTa and GPT-2, to the Telecom domain languages, and demonstrate a use case for identifying the 3rd Generation Partnership Project (3GPP) standard working groups. We consider training the selected models on 3GPP technical documents (Tdoc) pertinent to years 2009-2019 and predict the Tdoc categories in years 2020-2023. The results demonstrate that fine-tuning BERT and RoBERTa model achieves 84.6% accuracy, while GPT-2 model achieves 83% in identifying 3GPP working groups. The distilled BERT model with around 50% less parameters achieves similar performance as others. This corroborates that fine-tuning pretrained LLM can effectively identify the categories of Telecom language. The developed framework shows a stepping stone towards realizing intent-driven and self-evolving wireless networks from Telecom languages, and paves the way for the implementation of generative AI in the Telecom domain.

Minsu Kim, Walid Saad, Mohammad Mozaffari et al.

In this paper, a green-quantized FL framework, which represents data with a finite precision level in both local training and uplink transmission, is proposed. Here, the finite precision level is captured through the use of quantized neural networks (QNNs) that quantize weights and activations in fixed-precision format. In the considered FL model, each device trains its QNN and transmits a quantized training result to the base station. Energy models for the local training and the transmission with quantization are rigorously derived. To minimize the energy consumption and the number of communication rounds simultaneously, a multi-objective optimization problem is formulated with respect to the number of local iterations, the number of selected devices, and the precision levels for both local training and transmission while ensuring convergence under a target accuracy constraint. To solve this problem, the convergence rate of the proposed FL system is analytically derived with respect to the system control variables. Then, the Pareto boundary of the problem is characterized to provide efficient solutions using the normal boundary inspection method. Design insights on balancing the tradeoff between the two objectives while achieving a target accuracy are drawn from using the Nash bargaining solution and analyzing the derived convergence rate. Simulation results show that the proposed FL framework can reduce energy consumption until convergence by up to 70\% compared to a baseline FL algorithm that represents data with full precision without damaging the convergence rate.

Christo Kurisummoottil Thomas, Christina Chaccour, Walid Saad et al.

Despite the basic premise that next-generation wireless networks (e.g., 6G) will be artificial intelligence (AI)-native, to date, most existing efforts remain either qualitative or incremental extensions to existing "AI for wireless" paradigms. Indeed, creating AI-native wireless networks faces significant technical challenges due to the limitations of data-driven, training-intensive AI. These limitations include the black-box nature of the AI models, their curve-fitting nature, which can limit their ability to reason and adapt, their reliance on large amounts of training data, and the energy inefficiency of large neural networks. In response to these limitations, this article presents a comprehensive, forward-looking vision that addresses these shortcomings by introducing a novel framework for building AI-native wireless networks; grounded in the emerging field of causal reasoning. Causal reasoning, founded on causal discovery, causal representation learning, and causal inference, can help build explainable, reasoning-aware, and sustainable wireless networks. Towards fulfilling this vision, we first highlight several wireless networking challenges that can be addressed by causal discovery and representation, including ultra-reliable beamforming for terahertz (THz) systems, near-accurate physical twin modeling for digital twins, training data augmentation, and semantic communication. We showcase how incorporating causal discovery can assist in achieving dynamic adaptability, resilience, and cognition in addressing these challenges. Furthermore, we outline potential frameworks that leverage causal inference to achieve the overarching objectives of future-generation networks, including intent management, dynamic adaptability, human-level cognition, reasoning, and the critical element of time sensitivity.

Mohammad Karimzadeh Farshbafan, Walid Saad, Merouane Debbah

Goal-oriented semantic communication will be a pillar of next-generation wireless networks. Despite significant recent efforts in this area, most prior works are focused on specific data types (e.g., image or audio), and they ignore the goal and effectiveness aspects of semantic transmissions. In contrast, in this paper, a holistic goal-oriented semantic communication framework is proposed to enable a speaker and a listener to cooperatively execute a set of sequential tasks in a dynamic environment. A common language based on a hierarchical belief set is proposed to enable semantic communications between speaker and listener. The speaker, acting as an observer of the environment, utilizes the beliefs to transmit an initial description of its observation (called event) to the listener. The listener is then able to infer on the transmitted description and complete it by adding related beliefs to the transmitted beliefs of the speaker. As such, the listener reconstructs the observed event based on the completed description, and it then takes appropriate action in the environment based on the reconstructed event. An optimization problem is defined to determine the perfect and abstract description of the events while minimizing the transmission and inference costs with constraints on the task execution time and belief efficiency. Then, a novel bottom-up curriculum learning (CL) framework based on reinforcement learning is proposed to solve the optimization problem and enable the speaker and listener to gradually identify the structure of the belief set and the perfect and abstract description of the events. Simulation results show that the proposed CL method outperforms traditional RL in terms of convergence time, task execution cost and time, reliability, and belief efficiency.

Lina Bariah, Merouane Debbah

The evolution of network virtualization and native artificial intelligence (AI) paradigms have conceptualized the vision of future wireless networks as a comprehensive entity operating in whole over a digital platform, with smart interaction with the physical domain, paving the way for the blooming of the Digital Twin (DT) concept. The recent interest in the DT networks is fueled by the emergence of novel wireless technologies and use-cases, that exacerbate the level of complexity to orchestrate the network and to manage its resources. Driven by AI, the key principle of the DT is to create a virtual twin for the physical entities and network dynamics, where the virtual twin will be leveraged to generate synthetic data and offer an on-demand platform for AI model training. Despite the common understanding that AI is the seed for DT, we anticipate that the DT and AI will be enablers for each other, in a way that overcome their limitations and complement each other benefits. In this article, we dig into the fundamentals of DT, where we reveal the role of DT in unifying model-driven and data-driven approaches, and explore the opportunities offered by DT in order to achieve the optimistic vision of 6G networks. We further unfold the essential role of the theoretical underpinnings in unlocking further opportunities by AI, and hence, we unveil their pivotal impact on the realization of reliable, efficient, and low-latency DT.

Omar Hashash, Christina Chaccour, Walid Saad et al.

The wireless metaverse will create diverse user experiences at the intersection of the physical, digital, and virtual worlds. These experiences will enable novel interactions between the constituents (e.g., extended reality (XR) users and avatars) of the three worlds. However, remarkably, to date, there is no holistic vision that identifies the full set of metaverse worlds, constituents, and experiences, and the implications of their associated interactions on next-generation communication and computing systems. In this paper, we present a holistic vision of a limitless, wireless metaverse that distills the metaverse into an intersection of seven worlds and experiences that include the: i) physical, digital, and virtual worlds, along with the ii) cyber, extended, live, and parallel experiences. We then articulate how these experiences bring forth interactions between diverse metaverse constituents, namely, a) humans and avatars and b) connected intelligence systems and their digital twins (DTs). Then, we explore the wireless, computing, and artificial intelligence (AI) challenges that must be addressed to establish metaverse-ready networks that support these experiences and interactions. We particularly highlight the need for end-to-end synchronization of DTs, and the role of human-level AI and reasoning abilities for cognitive avatars. Moreover, we articulate a sequel of open questions that should ignite the quest for the future metaverse. We conclude with a set of recommendations to deploy the limitless metaverse over future wireless systems.

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

Large Language Models (LLMs) are increasingly used as high level controllers for autonomous Unmanned Aerial Vehicle (UAV) missions. However, existing evaluations rarely assess whether such agents remain safe, protocol compliant, and effective under realistic next generation networking constraints. This paper introduces $α^3$-Bench, a benchmark for evaluating LLM driven UAV autonomy as a multi turn conversational reasoning and control problem operating under dynamic 6G conditions. Each mission is formulated as a language mediated control loop between an LLM based UAV agent and a human operator, where decisions must satisfy strict schema validity, mission policies, speaker alternation, and safety constraints while adapting to fluctuating network slices, latency, jitter, packet loss, throughput, and edge load variations. To reflect modern agentic workflows, $α^3$-Bench integrates a dual action layer supporting both tool calls and agent to agent coordination, enabling evaluation of tool use consistency and multi agent interactions. We construct a large scale corpus of 113k conversational UAV episodes grounded in UAVBench scenarios and evaluate 17 state of the art LLMs using a fixed subset of 50 episodes per scenario under deterministic decoding. We propose a composite $α^3$ metric that unifies six pillars: Task Outcome, Safety Policy, Tool Consistency, Interaction Quality, Network Robustness, and Communication Cost, with efficiency normalized scores per second and per thousand tokens. Results show that while several models achieve high mission success and safety compliance, robustness and efficiency vary significantly under degraded 6G conditions, highlighting the need for network aware and resource efficient LLM based UAV agents. The dataset is publicly available on GitHub : https://github.com/maferrag/AlphaBench

Christina Chaccour, Walid Saad, Merouane Debbah et al.

In this paper a novel joint sensing, communication, and artificial intelligence (AI) framework is proposed so as to optimize extended reality (XR) experiences over terahertz (THz) wireless systems. The proposed framework consists of three main components. First, a tensor decomposition framework is proposed to extract unique sensing parameters for XR users and their environment by exploiting then THz channel sparsity. Essentially, THz band's quasi-opticality is exploited and the sensing parameters are extracted from the uplink communication signal, thereby allowing for the use of the same waveform, spectrum, and hardware for both communication and sensing functionalities. Then, the Cramer-Rao lower bound is derived to assess the accuracy of the estimated sensing parameters. Second, a non-autoregressive multi-resolution generative artificial intelligence (AI) framework integrated with an adversarial transformer is proposed to predict missing and future sensing information. The proposed framework offers robust and comprehensive historical sensing information and anticipatory forecasts of future environmental changes, which are generalizable to fluctuations in both known and unforeseen user behaviors and environmental conditions. Third, a multi-agent deep recurrent hysteretic Q-neural network is developed to control the handover policy of reconfigurable intelligent surface (RIS) subarrays, leveraging the informative nature of sensing information to minimize handover cost, maximize the individual quality of personal experiences (QoPEs), and improve the robustness and resilience of THz links. Simulation results show a high generalizability of the proposed unsupervised generative AI framework to fluctuations in user behavior and velocity, leading to a 61 % improvement in instantaneous reliability compared to schemes with known channel state information.

Marwa Chafii, Salmane Naoumi, Reda Alami et al.

In different wireless network scenarios, multiple network entities need to cooperate in order to achieve a common task with minimum delay and energy consumption. Future wireless networks mandate exchanging high dimensional data in dynamic and uncertain environments, therefore implementing communication control tasks becomes challenging and highly complex. Multi-agent reinforcement learning with emergent communication (EC-MARL) is a promising solution to address high dimensional continuous control problems with partially observable states in a cooperative fashion where agents build an emergent communication protocol to solve complex tasks. This paper articulates the importance of EC-MARL within the context of future 6G wireless networks, which imbues autonomous decision-making capabilities into network entities to solve complex tasks such as autonomous driving, robot navigation, flying base stations network planning, and smart city applications. An overview of EC-MARL algorithms and their design criteria are provided while presenting use cases and research opportunities on this emerging topic.

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

Emerging 6G visions, reflected in ongoing standardization efforts within 3GPP, IETF, ETSI, ITU-T, and the O-RAN Alliance, increasingly characterize networks as AI-native systems in which high-level semantic reasoning layers operate above standardized control and data-plane functions. Although frontier-scale large language models (LLMs) such as Qwen2.5-7B and Olmo-3-7B demonstrate strong reasoning capability, their computational footprint limits deployment in latency-sensitive, edge-native infrastructures. This paper presents a systematic empirical study of the scaling behavior and deployment efficiency of compact language models for network-level semantic reasoning in AI-native 6G systems. Using 6G-Bench, a standardization-aligned benchmark comprising 30 decision-making tasks across five capability domains, we evaluate models ranging from 135M (SmolLM2-135M) to 7B parameters (Qwen2.5-7B), including mid-scale architectures such as Llama-3.2-1B, Granite-1B, and Qwen2.5-3B. Deterministic accuracy (pass@1) increases from 0.224 at 135M to 0.707 at 7B, but scaling gains are highly non-uniform. A pronounced stability transition occurs in the 1 to 1.5B range, where accuracy rises from 0.373 (Llama-3.2-1B) to 0.531 (Qwen2.5-1.5B) and the instability gap Delta_5 contracts from 0.356 to 0.138. Beyond 3B parameters, improvements diminish (+0.064 from 3B to 7B). Through single-query inference profiling and an Edge Score metric that normalizes accuracy by latency and memory footprint, we show that semantic reliability per unit edge resource does not scale monotonically with parameter count. Instead, mid-scale models (approximately 1.5 to 3B) achieve the most favorable balance between deterministic stability and computational efficiency, providing deployment-relevant guidance for AI-native 6G architectures. All scripts and results are publicly available at https://github.com/maferrag/6G-Bench

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

Autonomous unmanned aerial vehicle (UAV) systems are increasingly deployed in safety-critical, networked environments where they must operate reliably in the presence of malicious adversaries. While recent benchmarks have evaluated large language model (LLM)-based UAV agents in reasoning, navigation, and efficiency, systematic assessment of security, resilience, and trust under adversarial conditions remains largely unexplored, particularly in emerging 6G-enabled settings. We introduce $α^{3}$-SecBench, the first large-scale evaluation suite for assessing the security-aware autonomy of LLM-based UAV agents under realistic adversarial interference. Building on multi-turn conversational UAV missions from $α^{3}$-Bench, the framework augments benign episodes with 20,000 validated security overlay attack scenarios targeting seven autonomy layers, including sensing, perception, planning, control, communication, edge/cloud infrastructure, and LLM reasoning. $α^{3}$-SecBench evaluates agents across three orthogonal dimensions: security (attack detection and vulnerability attribution), resilience (safe degradation behavior), and trust (policy-compliant tool usage). We evaluate 23 state-of-the-art LLMs from major industrial providers and leading AI labs using thousands of adversarially augmented UAV episodes sampled from a corpus of 113,475 missions spanning 175 threat types. While many models reliably detect anomalous behavior, effective mitigation, vulnerability attribution, and trustworthy control actions remain inconsistent. Normalized overall scores range from 12.9% to 57.1%, highlighting a significant gap between anomaly detection and security-aware autonomous decision-making. We release $α^{3}$-SecBench on GitHub: https://github.com/maferrag/AlphaSecBench

Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi et al.

The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the power of pre-trained Large Language Models (LLMs) based on groundbreaking Transformer architectures. As the frequency and diversity of cybersecurity attacks continue to rise, the importance of incident detection has significantly increased. IoT devices are expanding rapidly, resulting in a growing need for efficient techniques to autonomously identify network-based attacks in IoT networks with both high precision and minimal computational requirements. This paper presents SecurityBERT, a novel architecture that leverages the Bidirectional Encoder Representations from Transformers (BERT) model for cyber threat detection in IoT networks. During the training of SecurityBERT, we incorporated a novel privacy-preserving encoding technique called Privacy-Preserving Fixed-Length Encoding (PPFLE). We effectively represented network traffic data in a structured format by combining PPFLE with the Byte-level Byte-Pair Encoder (BBPE) Tokenizer. Our research demonstrates that SecurityBERT outperforms traditional Machine Learning (ML) and Deep Learning (DL) methods, such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), in cyber threat detection. Employing the Edge-IIoTset cybersecurity dataset, our experimental analysis shows that SecurityBERT achieved an impressive 98.2% overall accuracy in identifying fourteen distinct attack types, surpassing previous records set by hybrid solutions such as GAN-Transformer-based architectures and CNN-LSTM models. With an inference time of less than 0.15 seconds on an average CPU and a compact model size of just 16.7MB, SecurityBERT is ideally suited for real-life traffic analysis and a suitable choice for deployment on resource-constrained IoT devices.

Yong Xiao, Yiwei Liao, Yingyu Li et al.

Semantic-aware communication is a novel paradigm that draws inspiration from human communication focusing on the delivery of the meaning of messages. It has attracted significant interest recently due to its potential to improve the efficiency and reliability of communication and enhance users' QoE. Most existing works focus on transmitting and delivering the explicit semantic meaning that can be directly identified from the source signal. This paper investigates the implicit semantic-aware communication in which the hidden information that cannot be directly observed from the source signal must be recognized and interpreted by the intended users. To this end, a novel implicit semantic-aware communication (iSAC) architecture is proposed for representing, communicating, and interpreting the implicit semantic meaning between source and destination users. A projection-based semantic encoder is proposed to convert the high-dimensional graphical representation of explicit semantics into a low-dimensional semantic constellation space for efficient physical channel transmission. To enable the destination user to learn and imitate the implicit semantic reasoning process of source user, a generative adversarial imitation learning-based solution, called G-RML, is proposed. Different from existing communication solutions, the source user in G-RML does not focus only on sending as much of the useful messages as possible; but, instead, it tries to guide the destination user to learn a reasoning mechanism to map any observed explicit semantics to the corresponding implicit semantics that are most relevant to the semantic meaning. Compared to the existing solutions, our proposed G-RML requires much less communication and computational resources and scales well to the scenarios involving the communication of rich semantic meanings consisting of a large number of concepts and relations.

Wenbin Li, Hakim Hacid, Ebtesam Almazrouei et al.

The union of Edge Computing (EC) and Artificial Intelligence (AI) has brought forward the Edge AI concept to provide intelligent solutions close to the end-user environment, for privacy preservation, low latency to real-time performance, and resource optimization. Machine Learning (ML), as the most advanced branch of AI in the past few years, has shown encouraging results and applications in the edge environment. Nevertheless, edge-powered ML solutions are more complex to realize due to the joint constraints from both edge computing and AI domains, and the corresponding solutions are expected to be efficient and adapted in technologies such as data processing, model compression, distributed inference, and advanced learning paradigms for Edge ML requirements. Despite the fact that a great deal of the attention garnered by Edge ML is gained in both the academic and industrial communities, we noticed the lack of a complete survey on existing Edge ML technologies to provide a common understanding of this concept. To tackle this, this paper aims at providing a comprehensive taxonomy and a systematic review of Edge ML techniques, focusing on the soft computing aspects of existing paradigms and techniques. We start by identifying the Edge ML requirements driven by the joint constraints. We then extensively survey more than twenty paradigms and techniques along with their representative work, covering two main parts: edge inference, and edge learning. In particular, we analyze how each technique fits into Edge ML by meeting a subset of the identified requirements. We also summarize Edge ML frameworks and open issues to shed light on future directions for Edge ML.

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

The rapid advancement of large language models (LLMs) has sparked growing interest in their integration into autonomous systems for reasoning-driven perception, planning, and decision-making. However, evaluating and training such agentic AI models remains challenging due to the lack of large-scale, structured, and safety-critical benchmarks. This paper introduces AgentDrive, an open benchmark dataset containing 300,000 LLM-generated driving scenarios designed for training, fine-tuning, and evaluating autonomous agents under diverse conditions. AgentDrive formalizes a factorized scenario space across seven orthogonal axes: scenario type, driver behavior, environment, road layout, objective, difficulty, and traffic density. An LLM-driven prompt-to-JSON pipeline generates semantically rich, simulation-ready specifications that are validated against physical and schema constraints. Each scenario undergoes simulation rollouts, surrogate safety metric computation, and rule-based outcome labeling. To complement simulation-based evaluation, we introduce AgentDrive-MCQ, a 100,000-question multiple-choice benchmark spanning five reasoning dimensions: physics, policy, hybrid, scenario, and comparative reasoning. We conduct a large-scale evaluation of fifty leading LLMs on AgentDrive-MCQ. Results show that while proprietary frontier models perform best in contextual and policy reasoning, advanced open models are rapidly closing the gap in structured and physics-grounded reasoning. We release the AgentDrive dataset, AgentDrive-MCQ benchmark, evaluation code, and related materials at https://github.com/maferrag/AgentDrive

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

Autonomous aerial systems increasingly rely on large language models (LLMs) for mission planning, perception, and decision-making, yet the lack of standardized and physically grounded benchmarks limits systematic evaluation of their reasoning capabilities. To address this gap, we introduce UAVBench, an open benchmark dataset comprising 50,000 validated UAV flight scenarios generated through taxonomy-guided LLM prompting and multi-stage safety validation. Each scenario is encoded in a structured JSON schema that includes mission objectives, vehicle configuration, environmental conditions, and quantitative risk labels, providing a unified representation of UAV operations across diverse domains. Building on this foundation, we present UAVBench_MCQ, a reasoning-oriented extension containing 50,000 multiple-choice questions spanning ten cognitive and ethical reasoning styles, ranging from aerodynamics and navigation to multi-agent coordination and integrated reasoning. This framework enables interpretable and machine-checkable assessment of UAV-specific cognition under realistic operational contexts. We evaluate 32 state-of-the-art LLMs, including GPT-5, ChatGPT-4o, Gemini 2.5 Flash, DeepSeek V3, Qwen3 235B, and ERNIE 4.5 300B, and find strong performance in perception and policy reasoning but persistent challenges in ethics-aware and resource-constrained decision-making. UAVBench establishes a reproducible and physically grounded foundation for benchmarking agentic AI in autonomous aerial systems and advancing next-generation UAV reasoning intelligence. To support open science and reproducibility, we release the UAVBench dataset, the UAVBench_MCQ benchmark, evaluation scripts, and all related materials on GitHub at https://github.com/maferrag/UAVBench

Fenghao Zhu, Bohao Wang, Zhaohui Yang et al.

Beamforming with large-scale antenna arrays has been widely used in recent years, which is acknowledged as an important part in 5G and incoming 6G. Thus, various techniques are leveraged to improve its performance, e.g., deep learning, advanced optimization algorithms, etc. Although its performance in many previous research scenarios with deep learning is quite attractive, usually it drops rapidly when the environment or dataset is changed. Therefore, designing effective beamforming network with strong robustness is an open issue for the intelligent wireless communications. In this paper, we propose a robust beamforming self-supervised network, and verify it in two kinds of different datasets with various scenarios. Simulation results show that the proposed self-supervised network with hybrid learning performs well in both classic DeepMIMO and new WAIR-D dataset with the strong robustness under the various environments. Also, we present the principle to explain the rationality of this kind of hybrid learning, which is instructive to apply with more kinds of datasets.

Li Wang, Chao Zhang, Qiyang Zhao et al.

The development of wireless sensing technologies, using signals such as Wi-Fi, infrared, and RF to gather environmental data, has significantly advanced within Internet of Things (IoT) systems. Among these, Radio Frequency (RF) sensing stands out for its cost-effective and non-intrusive monitoring of human activities and environmental changes. However, traditional RF sensing methods face significant challenges, including noise, interference, incomplete data, and high deployment costs, which limit their effectiveness and scalability. This paper investigates the potential of Generative AI (GenAI) to overcome these limitations within the IoT ecosystem. We provide a comprehensive review of state-of-the-art GenAI techniques, focusing on their application to RF sensing problems. By generating high-quality synthetic data, enhancing signal quality, and integrating multi-modal data, GenAI offers robust solutions for RF environment reconstruction, localization, and imaging. Additionally, GenAI's ability to generalize enables IoT devices to adapt to new environments and unseen tasks, improving their efficiency and performance. The main contributions of this article include a detailed analysis of the challenges in RF sensing, the presentation of innovative GenAI-based solutions, and the proposal of a unified framework for diverse RF sensing tasks. Through case studies, we demonstrate the effectiveness of integrating GenAI models, leading to advanced, scalable, and intelligent IoT systems.

Francesco Pantisano, Mehdi Bennis, Walid Saad et al.

The deployment of underlay small base stations (SBSs) is expected to significantly boost the spectrum efficiency and the coverage of next-generation cellular networks. However, the coexistence of SBSs underlaid to an existing macro-cellular network faces important challenges, notably in terms of spectrum sharing and interference management. In this paper, we propose a novel game-theoretic model that enables the SBSs to optimize their transmission rates by making decisions on the resource occupation jointly in the frequency and spatial domains. This procedure, known as interference draining, is performed among cooperative SBSs and allows to drastically reduce the interference experienced by both macro- and small cell users. At the macrocell side, we consider a modified water-filling policy for the power allocation that allows each macrocell user (MUE) to focus the transmissions on the degrees of freedom over which the MUE experiences the best channel and interference conditions. This approach not only represents an effective way to decrease the received interference at the MUEs but also grants the SBSs tier additional transmission opportunities and allows for a more agile interference management. Simulation results show that the proposed approach yields significant gains at both macrocell and small cell tiers, in terms of average achievable rate per user, reaching up to 37%, relative to the non-cooperative case, for a network with 150 MUEs and 200 SBSs.

Mohamed Amine Ferrag, Burak Kantarci, Lucas C. Cordeiro et al.

Federated edge learning can be essential in supporting privacy-preserving, artificial intelligence (AI)-enabled activities in digital twin 6G-enabled Internet of Things (IoT) environments. However, we need to also consider the potential of attacks targeting the underlying AI systems (e.g., adversaries seek to corrupt data on the IoT devices during local updates or corrupt the model updates); hence, in this article, we propose an anticipatory study for poisoning attacks in federated edge learning for digital twin 6G-enabled IoT environments. Specifically, we study the influence of adversaries on the training and development of federated learning models in digital twin 6G-enabled IoT environments. We demonstrate that attackers can carry out poisoning attacks in two different learning settings, namely: centralized learning and federated learning, and successful attacks can severely reduce the model's accuracy. We comprehensively evaluate the attacks on a new cyber security dataset designed for IoT applications with three deep neural networks under the non-independent and identically distributed (Non-IID) data and the independent and identically distributed (IID) data. The poisoning attacks, on an attack classification problem, can lead to a decrease in accuracy from 94.93% to 85.98% with IID data and from 94.18% to 30.04% with Non-IID.

Neveen Hijazi, Moayad Aloqaily, Bassem Ouni et al.

The development of the Internet of Things (IoT) has dramatically expanded our daily lives, playing a pivotal role in the enablement of smart cities, healthcare, and buildings. Emerging technologies, such as IoT, seek to improve the quality of service in cognitive cities. Although IoT applications are helpful in smart building applications, they present a real risk as the large number of interconnected devices in those buildings, using heterogeneous networks, increases the number of potential IoT attacks. IoT applications can collect and transfer sensitive data. Therefore, it is necessary to develop new methods to detect hacked IoT devices. This paper proposes a Feature Selection (FS) model based on Harris Hawks Optimization (HHO) and Random Weight Network (RWN) to detect IoT botnet attacks launched from compromised IoT devices. Distributed Machine Learning (DML) aims to train models locally on edge devices without sharing data to a central server. Therefore, we apply the proposed approach using centralized and distributed ML models. Both learning models are evaluated under two benchmark datasets for IoT botnet attacks and compared with other well-known classification techniques using different evaluation indicators. The experimental results show an improvement in terms of accuracy, precision, recall, and F-measure in most cases. The proposed method achieves an average F-measure up to 99.9\%. The results show that the DML model achieves competitive performance against centralized ML while maintaining the data locally.

Sotiris Chatzimiltis, Mahdi Boloursaz Mashhadi, Mohammad Shojafar et al.

Agentic AI systems are emerging as powerful tools for automating complex, multi-step tasks across various industries. One such industry is telecommunications, where the growing complexity of next-generation radio access networks (RANs) opens up numerous opportunities for applying these systems. Securing the RAN is a key area, particularly through automating the security compliance process, as traditional methods often struggle to keep pace with evolving specifications and real-time changes. In this article, we propose a framework that leverages LLM-based AI agents integrated with a retrieval-augmented generation (RAG) pipeline to enable intelligent and autonomous enforcement of security compliance. An initial case study demonstrates how an agent can assess configuration files for compliance with O-RAN Alliance and 3GPP standards, generate explainable justifications, and propose automated remediation if needed. We also highlight key challenges such as model hallucinations and vendor inconsistencies, along with considerations like agent security, transparency, and system trust. Finally, we outline future directions, emphasizing the need for telecom-specific LLMs and standardized evaluation frameworks.

Talal Algumaei, Ruben Solozabal, Reda Alami et al.

This work studies non-cooperative Multi-Agent Reinforcement Learning (MARL) where multiple agents interact in the same environment and whose goal is to maximize the individual returns. Challenges arise when scaling up the number of agents due to the resultant non-stationarity that the many agents introduce. In order to address this issue, Mean Field Games (MFG) rely on the symmetry and homogeneity assumptions to approximate games with very large populations. Recently, deep Reinforcement Learning has been used to scale MFG to games with larger number of states. Current methods rely on smoothing techniques such as averaging the q-values or the updates on the mean-field distribution. This work presents a different approach to stabilize the learning based on proximal updates on the mean-field policy. We name our algorithm Mean Field Proximal Policy Optimization (MF-PPO), and we empirically show the effectiveness of our method in the OpenSpiel framework.

Qiyang Zhao, Mehdi Bennis, Merouane Debbah et al.

Semantic communication enables intelligent agents to extract meaning (or semantics) of information via interaction, to carry out collaborative tasks. In this paper, we study semantic communication from a topological space perspective, in which higher-order data semantics live in a simplicial complex. Specifically, a transmitter first maps its data into a $k$-order simplicial complex and then learns its high-order correlations. The simplicial structure and corresponding features are encoded into semantic embeddings in latent space for transmission. Subsequently, the receiver decodes the structure and infers the missing or distorted data. The transmitter and receiver collaboratively train a simplicial convolutional autoencoder to accomplish the semantic communication task. Experiments are carried out on a real dataset of Semantic Scholar Open Research Corpus, where one part of the semantic embedding is missing or distorted during communication. Numerical results show that the simplicial convolutional autoencoder enabled semantic communication effectively rebuilds the simplicial features and infer the missing data with $95\%$ accuracy, while achieving stable performance under channel noise. In contrast, the conventional autoencoder enabled communication fails to infer any missing data. Moreover, our approach is shown to effectively infer the distorted data without prior simplicial structure knowledge at the receiver, by learning extracted semantic information during communications. Leveraging the topological nature of information, the proposed method is also shown to be more reliable and efficient compared to several baselines, notably at low signal-to-noise (SNR) levels.

Mohamed Amine Ferrag, Ammar Battah, Norbert Tihanyi et al.

Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the market adoption of software applications and systems. Traditional bug-fixing methods, such as static analysis, often produce false positives. While bounded model checking, a form of Formal Verification (FV), can provide more accurate outcomes compared to static analyzers, it demands substantial resources and significantly hinders developer productivity. Can Machine Learning (ML) achieve accuracy comparable to FV methods and be used in popular instant code completion frameworks in near real-time? In this paper, we introduce SecureFalcon, an innovative model architecture with only 121 million parameters derived from the Falcon-40B model and explicitly tailored for classifying software vulnerabilities. To achieve the best performance, we trained our model using two datasets, namely the FormAI dataset and the FalconVulnDB. The FalconVulnDB is a combination of recent public datasets, namely the SySeVR framework, Draper VDISC, Bigvul, Diversevul, SARD Juliet, and ReVeal datasets. These datasets contain the top 25 most dangerous software weaknesses, such as CWE-119, CWE-120, CWE-476, CWE-122, CWE-190, CWE-121, CWE-78, CWE-787, CWE-20, and CWE-762. SecureFalcon achieves 94% accuracy in binary classification and up to 92% in multiclassification, with instant CPU inference times. It outperforms existing models such as BERT, RoBERTa, CodeBERT, and traditional ML algorithms, promising to push the boundaries of software vulnerability detection and instant code completion frameworks.

Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah

Sixth-generation (6G) networks are increasingly envisioned as AI-native infrastructures integrating communication, sensing, and computing into a unified fabric. However, existing approaches remain largely optimization-centric, relying on closed-loop control with limited reasoning capability. In this paper, we argue for a paradigm shift toward Agentic AI-Native 6G, in which Large Language Model (LLM)-based agents operate as bounded, policy-governed reasoning entities within a semantic control plane layered above deterministic 3GPP infrastructure. We propose a four-layer architecture that integrates deterministic network infrastructure, semantic abstraction of intent and context, hierarchical reasoning, and a distributed multi-agent fabric spanning device, edge, and core domains. To assess feasibility, we develop a proof-of-concept agentic reasoning and orchestration framework and conduct an extensive empirical study using a domain-specific 6G benchmark under realistic deployment constraints. Our results reveal a fundamental tradeoff between reasoning capability and system efficiency, showing that no single model simultaneously satisfies latency, throughput, and accuracy requirements. Instead, heterogeneous deployment of LLM agents across the device--edge--core continuum is necessary to balance these constraints. We further demonstrate that quantization introduces non-uniform effects across models, reinforcing the need for system-level optimization rather than model-level compression alone. These findings establish agentic intelligence as a viable architectural direction for 6G and highlight key challenges in achieving scalable, trustworthy, and self-reasoning networks. All experimental results and evaluation scripts are publicly available to support reproducibility.

Ali Maatouk, Nicola Piovesan, Fadhel Ayed et al.

Large Language Models (LLMs), AI-driven models that can achieve general-purpose language understanding and generation, have emerged as a transformative force, revolutionizing fields well beyond Natural Language Processing (NLP) and garnering unprecedented attention. As LLM technology continues to progress, the telecom industry is facing the prospect of its impact on its landscape. To elucidate these implications, we delve into the inner workings of LLMs, providing insights into their current capabilities and limitations. We also examine the use cases that can be readily implemented in the telecom industry, streamlining tasks, such as anomalies resolutions and technical specifications comprehension, which currently hinder operational efficiency and demand significant manpower and expertise. Furthermore, we uncover essential research directions that deal with the distinctive challenges of utilizing the LLMs within the telecom domain. Addressing them represents a significant stride towards fully harnessing the potential of LLMs and unlocking their capabilities to the fullest extent within the telecom domain.

Ali Maatouk, Fadhel Ayed, Nicola Piovesan et al.

We introduce TeleQnA, the first benchmark dataset designed to evaluate the knowledge of Large Language Models (LLMs) in telecommunications. Comprising 10,000 questions and answers, this dataset draws from diverse sources, including standards and research articles. This paper outlines the automated question generation framework responsible for creating this dataset, along with how human input was integrated at various stages to ensure the quality of the questions. Afterwards, using the provided dataset, an evaluation is conducted to assess the capabilities of LLMs, including GPT-3.5 and GPT-4. The results highlight that these models struggle with complex standards related questions but exhibit proficiency in addressing general telecom-related inquiries. Additionally, our results showcase how incorporating telecom knowledge context significantly enhances their performance, thus shedding light on the need for a specialized telecom foundation model. Finally, the dataset is shared with active telecom professionals, whose performance is subsequently benchmarked against that of the LLMs. The findings illustrate that LLMs can rival the performance of active professionals in telecom knowledge, thanks to their capacity to process vast amounts of information, underscoring the potential of LLMs within this domain. The dataset has been made publicly accessible on GitHub.

Hang Zou, Qiyang Zhao, Yu Tian et al.

Large Language Models (LLMs) have the potential to revolutionize the Sixth Generation (6G) communication networks. However, current mainstream LLMs generally lack the specialized knowledge in telecom domain. In this paper, for the first time, we propose a pipeline to adapt any general purpose LLMs to a telecom-specific LLMs. We collect and build telecom-specific pre-train dataset, instruction dataset, preference dataset to perform continual pre-training, instruct tuning and alignment tuning respectively. Besides, due to the lack of widely accepted evaluation benchmarks in telecom domain, we extend existing evaluation benchmarks and proposed three new benchmarks, namely, Telecom Math Modeling, Telecom Open QnA and Telecom Code Tasks. These new benchmarks provide a holistic evaluation of the capabilities of LLMs including math modeling, Open-Ended question answering, code generation, infilling, summarization and analysis in telecom domain. Our fine-tuned LLM TelecomGPT outperforms state of the art (SOTA) LLMs including GPT-4, Llama-3 and Mistral in Telecom Math Modeling benchmark significantly and achieve comparable performance in various evaluation benchmarks such as TeleQnA, 3GPP technical documents classification, telecom code summary and generation and infilling.

Qiyang Zhao, Hang Zou, Mehdi Bennis et al.

In this work, we study the problem of semantic communication and inference, in which a student agent (i.e. mobile device) queries a teacher agent (i.e. cloud sever) to generate higher-order data semantics living in a simplicial complex. Specifically, the teacher first maps its data into a k-order simplicial complex and learns its high-order correlations. For effective communication and inference, the teacher seeks minimally sufficient and invariant semantic structures prior to conveying information. These minimal simplicial structures are found via judiciously removing simplices selected by the Hodge Laplacians without compromising the inference query accuracy. Subsequently, the student locally runs its own set of queries based on a masked simplicial convolutional autoencoder (SCAE) leveraging both local and remote teacher's knowledge. Numerical results corroborate the effectiveness of the proposed approach in terms of improving inference query accuracy under different channel conditions and simplicial structures. Experiments on a coauthorship dataset show that removing simplices by ranking the Laplacian values yields a 85% reduction in payload size without sacrificing accuracy. Joint semantic communication and inference by masked SCAE improves query accuracy by 25% compared to local student based query and 15% compared to remote teacher based query. Finally, incorporating channel semantics is shown to effectively improve inference accuracy, notably at low SNR values.

Zhonghao Lyu, Ming Xiao, Mikael Skoglund et al.

Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we develop a tractable approximation for quantization-induced inference distortion. Based on this approximation, we derive lower and upper bounds on the quantization rate-inference distortion function, characterizing its dependence on LAIM statistics, including the quantization bit-width. Next, we formulate a joint quantization bit-width and computation frequency design problem under delay and energy constraints, aiming to minimize the distortion upper bound while ensuring tightness through the corresponding lower bound. Extensive evaluations validate the proposed distortion approximation, the derived rate-distortion bounds, and the effectiveness of the proposed joint design. Particularly, simulations and real-world testbed experiments demonstrate the effectiveness of the proposed joint design in balancing inference quality, latency, and energy consumption in edge embodied AI systems.

Farhad Rezazadeh, Hatim Chergui, Merouane Debbah et al.

We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access network (O-RAN) near-real-time (Near-RT) control via counterfactual dynamics and a world modeling (WM) paradigm that learns an action-conditioned generative state space. This enables quantitative "what-if" forecasting beyond large language models (LLMs) as the primary modeling primitive. Actions such as physical resource blocks (PRBs) are treated as first-class control inputs in a causal world model, and both aleatoric and epistemic uncertainty are modeled for prediction and what-if analysis. An agentic, model predictive control (MPC)-based cross-entropy method (CEM) planner operates over short horizons, using prior-mean rollouts within data-driven PRB bounds to maximize a deterministic reward. The model couples multi-scale structured state-space mixtures (MS3M) with a compact stochastic latent to form WM-MS3M, summarizing key performance indicators (KPIs) histories and predicting next-step KPIs under hypothetical PRB sequences. On realistic O-RAN traces, WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference, enabling rare-event simulation and offline policy screening.

Xiumei Deng, Zehui Xiong, Binbin Chen et al.

Large language models (LLMs) are proliferating rapidly at the edge, delivering intelligent capabilities across diverse application scenarios. However, their practical deployment in collaborative scenarios confronts fundamental challenges: privacy vulnerabilities, communication overhead, and computational bottlenecks. To address these, we propose Federated Attention (FedAttn), which integrates the federated paradigm into the self-attention mechanism, creating a new distributed LLM inference framework that simultaneously achieves privacy protection, communication efficiency, and computational efficiency. FedAttn enables participants to perform local self-attention over their own token representations while periodically exchanging and aggregating Key-Value (KV) matrices across multiple Transformer blocks, collaboratively generating LLM responses without exposing private prompts. Further, we identify a structural duality between contextual representation refinement in FedAttn and parameter optimization in FL across private data, local computation, and global aggregation. This key insight provides a principled foundation for systematically porting federated optimization techniques to collaborative LLM inference. Building on this framework, we theoretically analyze how local self-attention computation within participants and heterogeneous token relevance among participants shape error propagation dynamics across Transformer blocks. Moreover, we characterize the fundamental trade-off between response quality and communication/computation efficiency, which is governed by the synchronization interval and the number of participants. Experimental results validate our theoretical analysis, and reveal significant optimization opportunities through sparse attention and adaptive KV aggregation, highlighting FedAttn's potential to deliver scalability and efficiency in real-world edge deployments.

Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Haithem Boussaid et al.

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully train or finetune their models predicting the target speech. This hinders their ability to generalize well beyond the training set and leads to performance degeneration under out-of-distribution challenging scenarios. Unlike previous works that involve auxiliary losses or complex training procedures and architectures, we propose a simple approach, named Lip2Vec that is based on learning a prior model. Given a robust visual speech encoder, this network maps the encoded latent representations of the lip sequence to their corresponding latents from the audio pair, which are sufficiently invariant for effective text decoding. The generated audio representation is then decoded to text using an off-the-shelf Audio Speech Recognition (ASR) model. The proposed model compares favorably with fully-supervised learning methods on the LRS3 dataset achieving 26 WER. Unlike SoTA approaches, our model keeps a reasonable performance on the VoxCeleb test set. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.

Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Eustache Le Bihan et al.

The Lip Reading Sentences-3 (LRS3) benchmark has primarily been the focus of intense research in visual speech recognition (VSR) during the last few years. As a result, there is an increased risk of overfitting to its excessively used test set, which is only one hour duration. To alleviate this issue, we build a new VSR test set named WildVSR, by closely following the LRS3 dataset creation processes. We then evaluate and analyse the extent to which the current VSR models generalize to the new test data. We evaluate a broad range of publicly available VSR models and find significant drops in performance on our test set, compared to their corresponding LRS3 results. Our results suggest that the increase in word error rates is caused by the models inability to generalize to slightly harder and in the wild lip sequences than those found in the LRS3 test set. Our new test benchmark is made public in order to enable future research towards more robust VSR models.

Omar Erak, Nouf Alabbasi, Omar Alhussein et al.

Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system based on the Phi-2 small language model (SLM) to serve as an oracle for communication networks. Our developed system leverages forward-looking semantic chunking to adaptively determine parsing breakpoints based on embedding similarity, enabling effective processing of diverse document formats. To handle the challenge of multiple similar contexts in technical standards, we employ a re-ranking algorithm to prioritize the most relevant retrieved chunks. Recognizing the limitations of Phi-2's small context window, we implement a recent technique, namely SelfExtend, to expand the context window during inference, which not only boosts the performance but also can accommodate a wider range of user queries and design requirements from customers to specialized technicians. For fine-tuning, we utilize the low-rank adaptation (LoRA) technique to enhance computational efficiency during training and enable effective fine-tuning on small datasets. Our comprehensive experiments demonstrate substantial improvements over existing question-answering approaches in the telecom domain, achieving performance that exceeds larger language models such as GPT-4 (which is about 880 times larger in size). This work presents a novel approach to leveraging SLMs for communication networks, offering a balance of efficiency and performance. This work can serve as a foundation towards agentic language models for networks.

Lina Bariah, Brahim Mefgouda, Farbod Tavakkoli et al.

The integration of large language model (LLM) agents into telecom networks introduces new challenges, related to intent recognition, tool execution, and resolution generation, while taking into consideration different operational constraints. In this paper, we introduce TelcoAgent-Bench and TelcoAgent-Metrics, a Telecom-specific benchmarking framework for evaluating multilingual telecom LLM agents. The proposed framework assesses the semantic understanding as well as process-level alignment with structured troubleshooting flows and stability across repeated scenario variations. Our contribution includes a structured suite of metrics that assess intent recognition, ordered tool execution, resolution correctness, and stability across scenario variations, with the aim of quantifying the reliability and operational consistency of LLM agents in telecom environments. The framework is designed to operate in both English and Arabic, to address the need for multilingual agent deployment in operational network environments. Our experimental results show that although recent instruct-tuned models can understand telecom problems in a reasonable way, they usually struggle to consistently follow the required troubleshooting steps and to maintain stable behavior when exposed to different variations of the same scenario. This performance gap becomes more pronounced in unconstrained and bilingual settings.

Esraa Fahmy Othman, Lina Bariah, Merouane Debbah

Beam alignment is a key challenge in directional mmWave and THz systems, where narrow beams require accurate yet low-overhead training. Existing learning-based approaches typically predict a single beam and do not quantify uncertainty, limiting adaptive beam sweeping. We recast beam alignment as a generative task and propose a conditional diffusion model that learns a probabilistic beam prior from compact geometric and multipath features. The learned priors guide top-$k$ sweeps and capture the SNR loss induced by limited probing. Using a ray-traced DeepMIMO scenario with an 8-beam DFT codebook, our best conditional diffusion model achieves strong ranking performance (Hit@1 $\approx 0.61$, Hit@3 $\approx 0.90$, Hit@5 $\approx 0.97$) while preserving SNR at small sweep budgets. Compared with a deterministic classifier baseline, diffusion improves Hit@1 by about 180\%. Results further highlight the importance of informative conditioning and the ability of diffusion sampling to flexibly trade accuracy for computational efficiency. The proposed diffusion framework achieves substantial improvements in small-$k$ Hit rates, translating into reduced beam training overhead and enabling low-latency, energy-efficient beam alignment for mmWave and THz systems while preserving received SNR.

Haithem Boussaid, Marc Heemskerk, Jimmy Siméon et al.

Purpose: Corporate R&D faces a persistent productivity paradox: rising investment and expanding scientific knowledge have not translated into proportional innovation output. In pharmaceuticals this is captured as Eroom's Law; analogous patterns appear across engineering, materials science, and healthcare. The core cause is not insufficient tools but cognitive saturation: researchers spend an increasing share of their effort on coordination, documentation, and data governance -- hidden work that displaces high-value hypothesis formation, interpretation, and strategic synthesis. Design/Methodology/Approach: The paper uses a Design Science Research (DSR) methodology. The artifact is the HARMONY operating model. Evidence is triangulated from four semi-structured expert interviews with senior R&D leaders across industrial, healthcare, and academic settings; a foresight scenario analysis projecting four plausible 2040 R&D futures; and pattern matching with documented agentic R&D deployments. Two non-negotiable design requirements guide the architecture: cognitive-load redistribution (DR1) and bounded autonomy with alignment (DR2). Findings: We propose HARMONY -- Hybrid Agentic Research Model for Organisational New Yield -- a four-pillar socio-technical architecture comprising ResOps (Industrialized Execution), the Control Tower (Strategic Visibility and Drift Detection), the Ethics Fabric (Bounded Autonomy by Design), and the Talent Studio (Sciencepreneur Capability). The model introduces the Sciencepreneur as the central human archetype in agentic R&D, and Orchestration Leverage as a candidate productivity metric suited to human-agent hybrid systems.

Adrien Basdevant, Camille François, Victor Storchan et al.

Over the past year, there has been a robust debate about the benefits and risks of open sourcing foundation models. However, this discussion has often taken place at a high level of generality or with a narrow focus on specific technical attributes. In part, this is because defining open source for foundation models has proven tricky, given its significant differences from traditional software development. In order to inform more practical and nuanced decisions about opening AI systems, including foundation models, this paper presents a framework for grappling with openness across the AI stack. It summarizes previous work on this topic, analyzes the various potential reasons to pursue openness, and outlines how openness varies in different parts of the AI stack, both at the model and at the system level. In doing so, its authors hope to provide a common descriptive framework to deepen a nuanced and rigorous understanding of openness in AI and enable further work around definitions of openness and safety in AI.

Vincenzo Colle, Mohamed Sana, Nicola Piovesan et al.

The increasing adoption of artificial intelligence in telecommunications has raised interest in the capability of Large Language Models (LLMs) to address domain-specific, mathematically intensive tasks. Although recent advancements have improved the performance of LLMs in general mathematical reasoning, their effectiveness within specialized domains, such as signal processing, network optimization, and performance analysis, remains largely unexplored. To address this gap, we introduce TeleMath, the first benchmark dataset specifically designed to evaluate LLM performance in solving mathematical problems with numerical solutions in the telecommunications domain. Comprising 500 question-answer (QnA) pairs, TeleMath covers a wide spectrum of topics in the telecommunications field. This paper outlines the proposed QnAs generation pipeline, starting from a selected seed of problems crafted by Subject Matter Experts. The evaluation of a wide range of open-source LLMs reveals that best performance on TeleMath is achieved by recent models explicitly designed for mathematical or logical reasoning. In contrast, general-purpose models, even those with a large number of parameters, often struggle with these challenges. We have released the dataset and the evaluation code to ease result reproducibility and support future research.

Abderrahmane Lakas, Mohamed Amine Ferrag, Merouane Debbah

Large language models (LLMs) show strong potential for Intelligent Transportation Systems (ITS), particularly in tasks requiring situational reasoning and multi-agent coordination. These capabilities make them well suited for cooperative driving, where rule-based approaches struggle in complex and dynamic traffic environments. Intersection management remains especially challenging due to conflicting right-of-way demands, heterogeneous vehicle priorities, and vehicle-specific kinematic constraints that must be resolved in real time. However, existing approaches typically use LLMs as auxiliary components on top of signal-based systems rather than as primary decision-makers. Signal controllers remain vehicle-agnostic, reservation-based methods lack intent awareness, and recent LLM-based systems still depend on signal infrastructure. In addition, LLM inference latency limits their use in sub-second control settings. We propose LISA (LLM-Based Intent-Driven Speed Advisory), a signal-free cognitive arbitration framework for autonomous intersection management. LISA uses an LLM to reason over declared vehicle intents, incorporating priority classes, queue pressure, and energy preferences. We evaluate LISA against fixed-cycle control, SCATS, AIM, and GLOSA across varying traffic loads. Results show that LISA reduces mean control delay by up to 89.1% and maintains Level of Service C while all non-LLM baselines degrade to Level of Service F. Under near-saturated demand, LISA reduces mean waiting time by 93% and peak queue length by 60.6% relative to fixed-cycle control. It also lowers fuel consumption by up to 48.8% and achieves 86.2% intent satisfaction, compared to 61.2% for the best non-LLM method. These results demonstrate that LLM-based reasoning can enable real-time, signal-free intersection management.

Mohamed Sana, Nicola Piovesan, Antonio De Domenico et al.

Root Cause Analysis (RCA) in mobile networks remains a challenging task due to the need for interpretability, domain expertise, and causal reasoning. In this work, we propose a lightweight framework that leverages Large Language Models (LLMs) for RCA. To do so, we introduce TeleLogs, a curated dataset of annotated troubleshooting problems designed to benchmark RCA capabilities. Our evaluation reveals that existing open-source reasoning LLMs struggle with these problems, underscoring the need for domain-specific adaptation. To address this issue, we propose a two-stage training methodology that combines supervised fine-tuning with reinforcement learning to improve the accuracy and reasoning quality of LLMs. The proposed approach fine-tunes a series of RCA models to integrate domain knowledge and generate structured, multi-step diagnostic explanations, improving both interpretability and effectiveness. Extensive experiments across multiple LLM sizes show significant performance gains over state-of-the-art reasoning and non-reasoning models, including strong generalization to randomized test variants. These results demonstrate the promise of domain-adapted, reasoning-enhanced LLMs for practical and explainable RCA in network operation and management.

Thomas Mongaillard, Samson Lasaulce, Othman Hicheur et al.

While traditional optimization and scheduling schemes are designed to meet fixed, predefined system requirements, future systems are moving toward user-driven approaches and personalized services, aiming to achieve high quality-of-experience (QoE) and flexibility. This challenge is particularly pronounced in wireless and digitalized energy networks, where users' requirements have largely not been taken into consideration due to the lack of a common language between users and machines. The emergence of powerful large language models (LLMs) marks a radical departure from traditional system-centric methods into more advanced user-centric approaches by providing a natural communication interface between users and devices. In this paper, for the first time, we introduce a novel architecture for resource scheduling problems by constructing three LLM agents to convert an arbitrary user's voice request (VRQ) into a resource allocation vector. Specifically, we design an LLM intent recognition agent to translate the request into an optimization problem (OP), an LLM OP parameter identification agent, and an LLM OP solving agent. To evaluate system performance, we construct a database of typical VRQs in the context of electric vehicle (EV) charging. As a proof of concept, we primarily use Llama 3 8B. Through testing with different prompt engineering scenarios, the obtained results demonstrate the efficiency of the proposed architecture. The conducted performance analysis allows key insights to be extracted. For instance, having a larger set of candidate OPs to model the real-world problem might degrade the final performance because of a higher recognition/OP classification noise level. All results and codes are open source.

Minsu Kim, Walid Saad, Merouane Debbah et al.

The large communication and computation overhead of federated learning (FL) is one of the main challenges facing its practical deployment over resource-constrained clients and systems. In this work, SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead. In SpaFL, a trainable threshold is defined for each filter/neuron to prune its all connected parameters, thereby leading to structured sparsity. To optimize the pruning process itself, only thresholds are communicated between a server and clients instead of parameters, thereby learning how to prune. Further, global thresholds are used to update model parameters by extracting aggregated parameter importance. The generalization bound of SpaFL is also derived, thereby proving key insights on the relation between sparsity and performance. Experimental results show that SpaFL improves accuracy while requiring much less communication and computing resources compared to sparse baselines. The code is available at https://github.com/news-vt/SpaFL_NeruIPS_2024