Disaggregated 5G/O-RAN edge multicast spans multiple vendors and administrative domains, creating a need for auditable trust signals that do not expose sensitive evidence or disrupt real-time media delivery. This paper presents ZK-TrustLLM, a three-plane architecture that preserves the real-time DTLS/RTP multicast media path while separating evidence retention from trust verification. The evidence plane stores audit artefacts off-chain using the InterPlanetary File System (IPFS) via content addressing (CIDs), while the trust plane records commitments, proof outcomes, and policy-triggering events on a permissioned blockchain. Zero-knowledge submissions prove that a reported score lies within an admissible range and is cryptographically bound to an evidence commitment, while raw evidence remains off-chain for authorised audit. Trust outputs can then drive multicast control policies such as Logical Key Hierarchy (LKH) rekeying or subgroup isolation. We implement and evaluate a 10-tenant prototype (50 submissions) on a local chain with co-located IPFS, observing predictable confirmation latency (p50=6 ms, p95=7 ms) with stable gas (mean ≈ 137,783). The released artefact includes executable baselines and NDJSON logs to support reproducible evaluation.
Fluid antenna (FA) has emerged as a highly promising candidate in wireless communications, attributed to its exceptional design flexibility and enhanced degrees of freedom (DoFs). This paper addresses the challenge of direction-of-arrival (DoA) estimation for closely spaced signals under low signal-to-noise ratio (SNR) and limited snapshot conditions. To tackle this issue, a dual-driven FA system is proposed, which synergistically integrates data-driven and model-driven paradigms. Drawing inspiration from the Toeplitz algorithm, a deep neural network (DNN)-based multi-layer perceptron (MLP) architecture is developed to learn the mapping relationship between input covariance matrices and labeled covariance matrices. To ensure the output covariance matrices are compatible with subsequent subspace-based search procedures, a constrained forward computation function is designed. Furthermore, a dual-constrained loss function is formulated to balance the numerical precision and structural consistency of the output covariance matrices. Simulation results demonstrate that the proposed method achieves significant performance improvements over conventional DoA estimation algorithms in terms of estimation accuracy.
Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate budgets. Many existing systems overfit their training data and degrade sharply at very low bit rates because they attempt to compress the entire signal. We introduce Foundation Model-Guided Semantic and Goal-Oriented Communication (FMSGOC), a framework that uses broad visual–linguistic Foundation Model priors to mitigate overfitting. It further improves rate efficiency by concentrating bits on sparse, goal-aligned anchors and relying on generative foundation-model priors to reconstruct the masked regions. By decoupling what to send from how to reconstruct, a vision–language foundation model selects and transmits a sparse set of semantic anchors, while a pretrained diffusion model, fine-tuned for masked completion, reconstructs the image at the receiver. In our experiments, FMSGOC reaches 0.039 bits per pixel (BPP), maintains high semantic fidelity (cosine similarity 0.87–0.90 on CIFAR-10), remains robust on previously unseen inputs (0.83–0.86 on ImageNet), and shows good perceptual similarity (0.1278/0.1558, CIFAR-10/ImageNet), outperforming strong end-to-end baselines at lower bit rates.
This paper focuses on the affine frequency division multiplexing (AFDM)-enabled low Earth orbit (LEO) satellite communication, which can not only achieve seamless global coverage but also guarantee reliable multi-user access in high-mobility scenarios. On this basis, we put forward a discrete affine Fourier transform (DAFT)-domain random access preamble design scheme based on a dual-offset chirp, which concatenates asymmetric frequency-shifted chirps to significantly enlarge the available preamble pool. In particular, we reveal that, in the presence of timing offsets, the magnitude spectrum of the received preamble after matched filtering exhibits equidistant and oppositely directed peak shifts, presenting a predictable signature that enables accurate multi-user timing advance (TA) estimation. Building on this property, we further develop a segmented correlation and index reorganization-aided orthogonal matching pursuit (SCIR-OMP) algorithm for joint user identification and TA estimation. Theoretical analysis and simulation results demonstrate that the proposed scheme achieves superior multi-user detection performance compared with state-of-the-art ones.
Large language models (LLMs) open new possibilities for agentic control in Open RAN, allowing operators to express intents in natural language while delegating low-level execution to autonomous agents. We present A1gent, an agentic RAN control stack that decouples reasoning from real-time actuation. A non-RT agentic rApp compiles operator goals into typed A1 policy instances, and three task-oriented near-RT agentic xApps enforce them through a deterministic loop with plane-scoped actuation - E2 for mobility and load steering, and O1 for energy orchestration. This agentic reasoning-execution split ensures auditable coordination between RAN intelligent controller (RIC) tiers, supported by encoded guardrails and a fixed-priority action merger for conflict governance. A training-free adaptive policy tuner then refines bounded parameters using KPI memory without retraining, sustaining predictable adaptation. By integrating intent-driven planning with deterministic near-RT execution, A1gent advances Open RAN toward verifiable, self-governing, and reproducible agentic intelligence.
Resource sharing in multi-tenant cloud environments enables cost efficiency but introduces the Noisy Neighbor problem, i.e., co-located workloads that unpredictably degrade each other's performance. Despite extensive research on detecting such effects, there are no explainable methodologies for quantifying the severity of impact and establishing causal relationships among tenants. We propose an analytical that combines controlled experimentation with multi-stage causal inference and validates it across 10 independent rounds in a Kubernetes testbed. Our methodology not only quantifies severe performance degradations (e.g., up to 67% in I/O-bound workloads under combined stress) but also statistically establishes causality through Granger causality analysis, revealing a 75% increase in causal links when the noisy neighbor activates. Furthermore, we identify unique "degradation signatures" for each resource contention vector (i.e., CPU, memory, disk, network), enabling diagnostic capabilities that go beyond anomaly detection. This work transforms the Noisy Neighbor from an elusive problem into a quantifiable, diagnosable phenomenon, providing cloud operators with actionable insights for SLA management and smart resource allocation.
Current architecture proposals within standards development organizations such as ETSI and 3GPP enable sensing capabilities in mobile networks; however, they do not include a repository for storing sensing data. Such a repository can be used for AI model training and to complement ongoing sensing service provisioning by improving efficiency and accuracy. One way of realizing this is through the fusion of historical sensing data with live sensing data. In this paper, we study historical and live sensing data fusion for Integrated Sensing and Communication in future 6G systems and introduce a Sensing Data Storage Function to store historical sensing data and sensing results. We show how the Sensing Data Storage Function can be used with other network functions in a 6G architecture proposition for Integrated Sensing and Communication. We validate our proposal with a measurement model and show performance improvements in terms of detection probability and false-alarm rate. The network functionality to fuse and process sensing data combines live sensing measurements with previously sensed historical sensing data using a map-aware hard filter that rejects detections consistent with known static structures. Our simulation illustrates that, for a traffic junction scenario, map-aware hard filtering substantially reduces false alarms without degrading detection probability.
Open Radio Access Network (RAN) enables flexible, AI-driven control of mobile networks through disaggregated, multi-vendor components. In this architecture, xApps handle real-time functions, whereas rApps in the non-real-time controller generate strategic policies. However, current rApp development remains largely manual, brittle, and poorly scalable as xApp diversity proliferates. In this work, we propose a Multi-Agentic AI framework to automate rApp policy generation and orchestration. The architecture integrates three specialized large language model (LLM)-based agents, Perception, Reasoning, and Refinement, supported by retrieval-augmented generation (RAG) and memory-based analogical reasoning. These agents collectively analyze potential conflicts, synthesize intent-aligned control pipelines, and incrementally refine deployment decisions. Experiments across diverse deployment scenarios demonstrate that the proposed system achieves over 70
Handover optimization in O-RAN faces growing challenges due to heterogeneous user mobility patterns and rapidly varying radio conditions. Existing ML-based handover schemes typically operate at the near-RT layer, which lack awareness of the mobility-mode and struggle to incorporate a longer-term predictive context. This paper proposes a multi-modal mobility-aware optimization framework in which all predictive intelligence, including mobility mode classification, short-horizon trajectory and RSRP forecasting, and a PPO Actor–Critic policy, runs entirely inside an rApp in the non-RT RIC. The rApp generates per-UE ranked neighbour-cell recommendations and delivers them to the existing handover xApp through the A1 interface. The xApp combines these rankings with instantaneous E2 measurements and performs the final standards-compliant handover decision. This hierarchical design preserves low-latency execution in the xApp while enabling the rApp to supply richer and mode-specific predictive guidance. Evaluation using mobility traces demonstrates that the proposed approach reduces ping-pong handover events and improves handover reliability compared to conventional 3GPP A3-based and ML-based baselines.
Modern 5G/6G radio access networks are increasingly programmable through O-RAN, yet their operational complexity has grown with disaggregation, open interfaces, and fine-grained control parameters. While RAN-side analytics and telemetry mechanisms, such as KPI-based monitoring and mobility event reporting, provide visibility into network behavior, operators still face challenges in correlating heterogeneous events and safely translating observations into actionable configuration changes. This paper presents an LLM-based Net Analyzer rApp for the O-RAN Non-RT RIC that enables explainable and safe, human-in-the-loop automation for RAN operations. The proposed rApp adopts an event-informed, batch-triggered reasoning framework in which mobility events are first interpreted, anomalies are confirmed through targeted log inspection, configurations are inspected via tool-gated access, and minimal configuration changes are proposed only after explicit operator approval. The architecture enforces a strict separation between reasoning and actuation, ensuring auditability and operational safety. The system is implemented and demonstrated on a real O-RAN testbed using a reproducible ping-pong handover scenario, illustrating how large language models can function as reasoning co-pilots that transform raw RAN telemetry into structured explanations and controlled remediation workflows, complementing existing analytics-only approaches in the NonRT RIC.
In Earth observation (EO) missions with Low Earth orbit (LEO) satellites, high-resolution image acquisition generates a massive data volume that poses a significant challenge for transmission under the limited satellite power budget, while LEO movement introduces dynamic systems. To enable efficient image transmission, this paper employs semantic communication (SemCom) with joint source-channel coding (JSCC), which focuses on transmitting meaningful information to reduce power consumption. Under a quality-of-service (QoS) requirement defined by image reconstruction quality, this work aims to minimize the total transmit power by jointly optimizing the JSCC encoder-decoder parameters and resource allocation. However, the implicit relationship among JSCC parameters, link quality, and image quality, coupled with the presence of mixed integer-continuous variables, makes the problem difficult to solve directly. To address this, a curve-fitting model is proposed to approximate the JSCC compression-SNR-quality relationship. Then, the joint compression ratio-resource allocation (JCRRA) algorithm is proposed to address the underlying problem. Numerical results demonstrate that the proposed method achieves substantial power savings compared to both greedy algorithms and conventional transmission paradigms.
We study the allocation of reconfigurable intelligent surfaces (RISs) in a multi-cell wireless network, where base stations compete for control of shared RIS units deployed at the cell edges. These RISs, provided by an independent operator, are dynamically leased to the highest bidder using a simultaneously ascending auction format. Each base station estimates the utility of acquiring additional RISs based on macroscopic channel parameters, enabling a scalable and low-overhead allocation mechanism. To optimize the bidding behavior, we integrate deep reinforcement learning (DRL) agents that learn to maximize performance while adhering to budget constraints. Through simulations in clustered cell-edge environments, we demonstrate that reinforcement learning (RL)-based bidding significantly outperforms heuristic strategies, achieving optimal trade-offs between cost and spectral efficiency. Furthermore, we introduce a tunable parameter that governs the bidding aggressiveness of RL agents, enabling a flexible control of the trade-off between network performance and expenditure. Our results highlight the potential of combining auction-based allocation with adaptive RL mechanisms for efficient and fair utilization of RISs in next-generation wireless networks.
Agentic artificial intelligence (AI) is emerging as a key enabler for autonomous radio access networks (RANs), where multiple large language model (LLM)-based agents reason and collaborate to achieve operator-defined intents. The open RAN (O-RAN) architecture enables the deployment and coordination of such agents. However, most existing works consider simple intents handled by independent agents, while complex intents that require coordination among agents remain unexplored. In this paper, we propose an agentic AI framework for intent translation and optimization in cell-free O-RAN. A supervisor agent translates the operator intents into an optimization objective and minimum rate requirements. Based on this information, a user weighting agent retrieves relevant prior experience from a memory module to determine the user priority weights for precoding. If the intent includes an energy-saving objective, then an open radio unit (O-RU) management agent will also be activated to determine the set of active O-RUs by using a deep reinforcement learning (DRL) algorithm. A monitoring agent measures and monitors the user data rates and coordinates with other agents to guarantee the minimum rate requirements are satisfied. To enhance scalability, we adopt a parameter-efficient fine-tuning (PEFT) method that enables the same underlying LLM to be used for different agents. Simulation results show that the proposed agentic AI framework reduces the number of active O-RUs by 41.93
This paper investigates the problem of minimizing total energy consumption for secure federated learning (FL) in wireless edge networks, a key paradigm for decentralized big data analytics. To tackle the high computational cost and privacy challenges of processing large-scale distributed data with conventional neural networks, we propose an FL with hyperdimensional computing and differential privacy (FL-HDC-DP) framework. Each edge device employs hyperdimensional computing (HDC) for lightweight local training and applies differential privacy (DP) noise to protect transmitted model updates. The total energy consumption is minimized through a joint optimization of the HDC dimension, transmit power, and CPU frequency. An efficient hybrid algorithm is developed, combining an outer enumeration search for HDC dimensions with an inner one-dimensional search for resource allocation. Simulation results show that the proposed framework achieves up to 83.3
This paper proposes a novel optimization framework for enhancing the security resilience of cell-free massive multiple-input multiple-output (CF-mMIMO) networks with multi-antenna access points (APs) and protective partial zero-forcing (PPZF) under active eavesdropping. Based on the main principles of absorption, adaptation, and recovery, we formulate a security-aware resilience metric to quantify the system performance during and after a security outage. A multi-user service priority-aware power allocation problem is formulated to minimize the mean squared error (MSE) between real-time and desired security efficiency, thereby enabling a trade-off between the target user's secrecy performance and multi-user quality of service (QoS). To solve this non-convex problem, a security-aware iterative algorithm based on the successive convex approximation (SCA) is employed. The proposed algorithm determines the optimal power allocation strategy by balancing solution quality against recovery time. At each iteration, it evaluates the overall resilience score and selects the strategy that achieves the highest value. Simulation results confirm that the proposed framework significantly improves the resilience of CF-mMIMO networks, allowing flexible adaptation between rapid recovery and high-quality recovery, depending on system requirements.
We study the optimal transmission and scheduling policy for a transmitter (source) communicating with two gossiping receivers aiming at tracking the source's status over time using the age of information (AoI) metric. Gossiping enables local information exchange in a decentralized manner without relying solely on the transmitter's direct communication, which we assume incurs a transmission cost. On the other hand, gossiping may be communicating stale information, necessitating the transmitter's intervention. With communication links having specific success probabilities, we formulate an average-cost Markov Decision Process (MDP) to jointly minimize the sum AoI and transmission cost for such a system in a time-slotted setting. We employ the Relative Value Iteration (RVI) algorithm to evaluate the optimal policy for the transmitter and then prove several structural properties showing that it has an age-difference threshold structure with minimum age activation in the case where gossiping is relatively more reliable. Specifically, direct transmission is optimal only if the minimum AoI of the receivers is large enough and their age difference is below a certain threshold. Otherwise, the transmitter idles to effectively take advantage of gossiping and reduce direct transmission costs. Numerical evaluations demonstrate the significance of our optimal policy compared to multiple baselines. Our result is a first step towards characterizing optimal freshness and transmission cost trade-offs in gossiping networks.
Sixth-generation (6G) radio access networks (RANs) must enforce strict service-level agreements (SLAs) for heterogeneous slices, yet sudden latency spikes remain difficult to diagnose and resolve with conventional deep reinforcement learning (DRL) or explainable RL (XRL). We propose \emph{Attention-Enhanced Multi-Agent Proximal Policy Optimization (AE-MAPPO)}, which integrates six specialized attention mechanisms into multi-agent slice control and surfaces them as zero-cost, faithful explanations. The framework operates across O-RAN timescales with a three-phase strategy: predictive, reactive, and inter-slice optimization. A URLLC case study shows AE-MAPPO resolves a latency spike in $18$ms, restores latency to $0.98$ms with $99.9999\%$ reliability, and reduces troubleshooting time by $93\%$ while maintaining eMBB and mMTC continuity. These results confirm AE-MAPPO's ability to combine SLA compliance with inherent interpretability, enabling trustworthy and real-time automation for 6G RAN slicing.
We study federated learning (FL) over wireless fading channels where multiple devices simultaneously send their model updates. We propose an efficient age-aware edge-blind over-the-air FL approach that does not require channel state information (CSI) at the devices. Instead, the parameter server (PS) uses multiple antennas and applies maximum-ratio combining (MRC) based on its estimated sum of the channel gains to detect the parameter updates. A key challenge is that the number of orthogonal subcarriers is limited; thus, transmitting many parameters requires multiple Orthogonal Frequency Division Multiplexing (OFDM) symbols, which increases latency. To address this, the PS selects only a small subset of model coordinates each round using AgeTop-k, which first picks the largest-magnitude entries and then chooses the k coordinates with the longest waiting times since they were last selected. This ensures that all selected parameters fit into a single OFDM symbol, reducing latency. We provide a convergence bound that highlights the advantages of using a higher number of antenna array elements and demonstrates a key trade-off: increasing k decreases compression error at the cost of increasing the effect of channel noise. Experimental results show that (i) more PS antennas greatly improve accuracy and convergence speed; (ii) AgeTop-k outperforms random selection under relatively good channel conditions; and (iii) the optimum k depends on the channel, with smaller k being better in noisy settings.
Recent advancements in mobile and wireless networks are unlocking the full potential of robotic autonomy, enabling robots to take advantage of ultra-low latency, high data throughput, and ubiquitous connectivity. However, for robots to navigate and operate seamlessly, efficiently and reliably, they must have an accurate understanding of both their surrounding environment and the quality of radio signals. Achieving this in highly dynamic and ever-changing environments remains a challenging and largely unsolved problem. In this paper, we introduce MapViT, a two-stage Vision Transformer (ViT)-based framework inspired by the success of pre-train and fine-tune paradigm for Large Language Models (LLMs). MapViT is designed to predict both environmental changes and expected radio signal quality. We evaluate the framework using a set of representative Machine Learning (ML) models, analyzing their respective strengths and limitations across different scenarios. Experimental results demonstrate that the proposed two-stage pipeline enables real-time prediction, with the ViT-based implementation achieving a strong balance between accuracy and computational efficiency. This makes MapViT a promising solution for energy- and resource-constrained platforms such as mobile robots. Moreover, the geometry foundation model derived from the self-supervised pre-training stage improves data efficiency and transferability, enabling effective downstream predictions even with limited labeled data. Overall, this work lays the foundation for next-generation digital twin ecosystems, and it paves the way for a new class of ML foundation models driving multi-modal intelligence in future 6G-enabled systems.
In disaster scenarios, ensuring both reliable communication and situational awareness becomes a critical challenge due to the partial or complete collapse of terrestrial networks. This paper proposes an integrated sensing and communication (ISAC) over non-terrestrial networks (NTN) architecture referred to as ISAC-over-NTN that integrates multiple uncrewed aerial vehicles (UAVs) and a high-altitude platform station (HAPS) to maintain resilient and reliable network operations in post-disaster conditions. We aim to achieve two main objectives: i) provide a reliable communication infrastructure, thereby ensuring the continuity of search-and-rescue activities and connecting people to their loved ones, and ii) detect users, such as those trapped under rubble or those who are mobile, using a Doppler-based mobility detection model. We employ an innovative beamforming method that simultaneously transmits data and detects Doppler-based mobility by integrating multi-user multiple-input multiple-output (MU-MIMO) communication and monostatic sensing within the same transmission chain. The results show that the proposed framework maintains reliable connectivity and achieves high detection accuracy of users in critical locations, reaching 90
