Searcharxiv⌕ Search

arXiv subjects

Merouane Debbah

Publications and source records attributed to Merouane Debbah.

At least 55 records · Page 3Linked to original sources
arXiv2026

TelcoAgent-Bench: A Multilingual Benchmark for Telecom AI Agents

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.

cs.CL↗
arXiv2026

Neural Precoding in Complex Projective Spaces

Deep-learning (DL)-based precoding in multi-user multiple-input single-output (MU-MISO) systems involves training DL models to map features derived from channel coefficients to labels derived from precoding weights. Traditionally, complex-valued channel and precoder coefficients are parameterized using either their real and imaginary components or their amplitude and phase. However, precoding performance depends on magnitudes of inner products between channel and precoding vectors, which are invariant to global phase rotations. Conventional representations fail to exploit this symmetry, leading to inefficient learning and degraded generalization. To address this, we propose a DL framework based on complex projective space (CPS) parameterizations of both the wireless channel and the weighted minimum mean squared error (WMMSE) precoder vectors. By removing the global phase redundancies inherent in conventional representations, the proposed framework enables the DL model to learn geometry-aligned and physically distinct channel-precoder mappings. Two CPS parameterizations based on real-valued embeddings and complex hyperspherical coordinates are investigated and benchmarked against two baseline methods. Simulation results demonstrate substantial improvements in sum-rate performance and generalization, with negligible increase in model complexity.

cs.LG↗
arXiv2026

From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review

Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. Driven by the growing need for standardized evaluation and integration, we systematically consolidate these fragmented efforts into a unified framework. However, the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey. Therefore, we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains. In addition, we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments. Furthermore, we review AI-agent frameworks introduced between 2023 and 2025 that integrate large language models with modular toolkits to enable autonomous decision-making and multi-step reasoning. Moreover, we present real-world applications of autonomous AI agents in materials science, biomedical research, academic ideation, software engineering, synthetic data generation, chemical reasoning, mathematical problem-solving, geographic information systems, multimedia, healthcare, and finance. We then survey key agent-to-agent collaboration protocols, namely the Agent Communication Protocol (ACP), the Model Context Protocol (MCP), and the Agent-to-Agent Protocol (A2A). Finally, we discuss recommendations for future research, focusing on advanced reasoning strategies, failure modes in multi-agent LLM systems, automated scientific discovery, dynamic tool integration via reinforcement learning, integrated search capabilities, and security vulnerabilities in agent protocols.

cs.AI↗
arXiv2026

Large Language Models as Bidding Agents in Repeated HetNet Auction

This paper investigates the integration of large language models (LLMs) as reasoning agents in repeated spectrum auctions within heterogeneous networks (HetNets). While auction-based mechanisms have been widely employed for efficient resource allocation, most prior works assume one-shot auctions, static bidder behavior, and idealized conditions. In contrast to traditional formulations where base station (BS) association and power allocation are centrally optimized, we propose a distributed auction-based framework in which each BS independently conducts its own multi-channel auction, and user equipments (UEs) strategically decide both their association and bid values. Within this setting, UEs operate under budget constraints and repeated interactions, transforming resource allocation into a long-term economic decision rather than a one-shot optimization problem. The proposed framework enables the evaluation of diverse bidding behaviors -from classical myopic and greedy policies to LLM-based agents capable of reasoning over historical outcomes, anticipating competition, and adapting their bidding strategy across episodes. Simulation results reveal that the LLM-empowered UE consistently achieves higher channel access frequency and improved budget efficiency compared to benchmarks. These findings highlight the potential of reasoning-enabled agents in future decentralized wireless networks markets and pave the way for lightweight, edge-deployable LLMs to support intelligent resource allocation in next-generation HetNets.

cs.NI↗
arXiv2026

Quantization-Aware Collaborative Inference for Large Embodied AI Models

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.

cs.LG↗
arXiv2026

6G-Bench: An Open Benchmark for Semantic Communication and Network-Level Reasoning with Foundation Models in AI-Native 6G Networks

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

cs.NI↗
arXiv2026

A Mode-Matching Approach to the Design of RIS-Aided Communications

Reconfigurable intelligent surface (RIS) is an emerging technology for application to wireless communications. In this paper, we consider the problem of anomalous reflection and model the RIS as a periodic surface impedance boundary. We utilize the mode matching method and Floquets expansion representation to compute the field reflected from a spatially periodic RIS, and evaluate the performance versus implementation complexity tradeoffs of RIS aided communications based on the global design criterion. This allows us to maximize the power reflected towards the intended direction of propagation, while minimizing the power reradiated towards undesired directions of propagation. In addition, we discuss the advantages of the proposed electromagnetically consistent approach to the design of RIS aided wireless systems.

math.OC↗
arXiv2026

Comparative Analysis of Differential and Collision Entropy for Finite-Regime QKD in Hybrid Quantum Noisy Channels

In this work, a comparative study between three fundamental entropic measures, differential entropy, quantum Renyi entropy, and quantum collision entropy for a hybrid quantum channel (HQC) was investigated, where hybrid quantum noise (HQN) is characterized by both discrete and continuous variables (CV) noise components. Using a Gaussian mixture model (GMM) to statistically model the HQN, we construct as well as visualize the corresponding pointwise entropic functions in a given 3D probabilistic landscape. When integrated over the relevant state space, these entropic surfaces yield values of the respective global entropy. Through analytical and numerical evaluation, it is demonstrated that the differential entropy approaches the quantum collision entropy under certain mixing conditions, which aligns with the Renyi entropy for order $α= 2$. Within the HQC framework, the results establish a theoretical and computational equivalence between these measures. This provides a unified perspective on quantifying uncertainty in hybrid quantum communication systems. Extending the analysis to the operational domain of finite key QKD, we demonstrated that the same $10\%$ approximation threshold corresponds to an order-of-magnitude change in Eves success probability and a measurable reduction in the secure key rate.

eess.SP↗
arXiv2026

$α^3$-SecBench: A Large-Scale Evaluation Suite of Security, Resilience, and Trust for LLM-based UAV Agents over 6G Networks

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

cs.CR↗
arXiv2026

AgentDrive: An Open Benchmark Dataset for Agentic AI Reasoning with LLM-Generated Scenarios in Autonomous Systems

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

cs.AI↗
arXiv2026

One-Step Generative Channel Estimation via Average Velocity Field

Generative models have shown immense potential for wireless communication by learning complex channel data distributions. However, the iterative denoising process associated with these models imposes a significant challenge in latency-sensitive wireless communication scenarios, particularly in channel estimation. To address this challenge, we propose a novel solution for one-step generative channel estimation. Our approach bypasses the time-consuming iterative steps of conventional models by directly learning the average velocity field. Through extensive simulations, we validate the effectiveness of our proposed method over existing state-of-the-art diffusion-based approach. Specifically, our scheme achieves a normalized mean squared error up to 2.65 dB lower than the diffusion method and reduces latency by around 90%, demonstrating the potential of our method to enhance channel estimation performance.

cs.IT↗
arXiv2026

Reasoning Beyond Limits: Advances and Open Problems for LLMs

Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning chains. Techniques such as inference-time scaling, reinforcement learning, supervised fine-tuning, and distillation have been effectively applied to state-of-the-art models, including DeepSeek-R1, OpenAI o1 and o3, GPT-4o, Qwen-32B, and various Llama variants, significantly enhancing their reasoning capabilities. In this paper, we present a comprehensive review of the top 27 LLMs released between 2023 and 2025, such as Mistral AI Small 3 24B, DeepSeek-R1, Search-o1, QwQ-32B, and Phi-4, and analyze their core innovations and performance improvements. We also provide a detailed overview of recent advancements in multilingual large language models (MLLMs), emphasizing methods that improve cross-lingual reasoning and address the limitations of English-centric training. In parallel, we present a comprehensive review of progress in state space model (SSM)-based architectures, including models such as Mamba, which demonstrate improved efficiency for long-context processing compared to transformer-based approaches. Our analysis covers training strategies including general optimization techniques, mixture-of-experts (MoE) configurations, retrieval-augmented generation (RAG), chain-of-thought prompting, self-improvement methods, and test-time compute scaling and distillation frameworks. Finally, we identify key challenges for future research, including enabling multi-step reasoning without human supervision, improving robustness in chained task execution, balancing structured prompting with generative flexibility, and enhancing the integration of long-context retrieval and external tools.

cs.LG↗
arXiv2026

$α^3$-Bench: A Unified Benchmark of Safety, Robustness, and Efficiency for LLM-Based UAV Agents over 6G Networks

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

eess.SY↗
arXiv2025

Context Video Semantic Transmission with Variable Length and Rate Coding over MIMO Channels

The evolution of semantic communications has profoundly impacted wireless video transmission, whose applications dominate driver of modern bandwidth consumption. However, most existing schemes are predominantly optimized for simple additive white Gaussian noise or Rayleigh fading channels, neglecting the ubiquitous multiple-input multiple-output (MIMO) environments that critically hinder practical deployment. To bridge this gap, we propose the context video semantic transmission (CVST) framework under MIMO channels. Building upon an efficient contextual video transmission backbone, CVST effectively learns a context-channel correlation map to explicitly formulate the relationships between feature groups and MIMO subchannels. Leveraging these channel-aware features, we design a multi-reference entropy coding mechanism, enabling channel state-aware variable length coding. Furthermore, CVST incorporates a checkerboard-based feature modulation strategy to achieve multiple rate points within a single trained model, thereby enhancing deployment flexibility. These innovations constitute our multi-reference variable length and rate coding (MR-VLRC) scheme. By integrating contextual transmission with MR-VLRC, CVST demonstrates substantial performance gains over various standardized separated coding methods and recent wireless video semantic communication approaches. The code is available at https://github.com/xie233333/CVST.

cs.IT↗
arXiv2025

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and inter-agent protocols has outpaced security practices, leading to brittle integrations that rely on ad-hoc authentication, inconsistent schemas, and weak validation. This survey introduces a unified end-to-end threat model for LLM-agent ecosystems, covering host-to-tool and agent-to-agent communications. We systematically categorize more than thirty attack techniques spanning input manipulation, model compromise, system and privacy attacks, and protocol-level vulnerabilities. For each category, we provide a formal threat formulation defining attacker capabilities, objectives, and affected system layers. Representative examples include Prompt-to-SQL injections and the Toxic Agent Flow exploit in GitHub MCP servers. We analyze attack feasibility, review existing defenses, and discuss mitigation strategies such as dynamic trust management, cryptographic provenance tracking, and sandboxed agent interfaces. The framework is validated through expert review and cross-mapping with real-world incidents and public vulnerability repositories, including CVE and NIST NVD. Compared to prior surveys, this work presents the first integrated taxonomy bridging input-level exploits and protocol-layer vulnerabilities in LLM-agent ecosystems, offering actionable guidance for designing secure and resilient agentic AI systems.

cs.CR↗
arXiv2025

Lightweight Foundation Model for Wireless Time Series Downstream Tasks on Edge Devices

While machine learning is widely used to optimize wireless networks, training a separate model for each task in communication and localization is becoming increasingly unsustainable due to the significant costs associated with training and deployment. Foundation models offer a more scalable alternative by enabling a single model to be adapted across multiple tasks through fine-tuning with limited samples. However, current foundation models mostly rely on large-scale Transformer architectures, resulting in computationally intensive models unsuitable for deployment on typical edge devices. This paper presents a lightweight foundation model based on simple Multi-Layer-Perceptron (MLP) encoders that independently process input patches. Our model supports 4 types of downstream tasks (long-range technology recognition, short-range technology recognition, modulation recognition and line-of-sight-detection) from multiple input types (IQ and CIR) and different sampling rates. We show that, unlike Transformers, which can exhibit performance drops as downstream tasks are added, our MLP model maintains robust generalization performance, achieving over 97% accurate fine-tuning results for previously unseen data classes. These results are achieved despite having only 21K trainable parameters, allowing an inference time of 0.33 ms on common edge devices, making the model suitable for constrained real-time deployments.

eess.SP↗
arXiv2025

UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios

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

cs.AI↗
arXiv2025

Federated Attention: A Distributed Paradigm for Collaborative LLM Inference over Edge Networks

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.

cs.DC↗