arXiv subjects

Nicola Piovesan

Publications and source records attributed to Nicola Piovesan.

At least 19 recordsLinked to original sources

arXiv2026

CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations

Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints. However, existing evaluations fail to accurately model real network characteristics or assess agents under partially observable telecom environments with diverse vendors, devices, protocols, and interfaces. In this paper, we introduce CTBench, a public benchmark for assessing whether an agent behaves like a competent telecom troubleshooting engineer. CTBench focuses on root cause analysis and path restoration. Each task is constructed by experts and annotated with rich task metadata, including golden evidence steps. CTBench uses expert-grounded metrics that evaluate both final answers and the diagnostic evidence. Experiments with representative harness-model combinations show that state-of-the-art agents perform very well at identifying endpoints in path-restoration tasks but, more generally, underperform in root cause analysis. In particular, agents struggle with interface state, link-layer, service-management, and other operational faults. Most importantly, even when agents produce plausible or correct final answers, they often fail to provide the evidence-grounded diagnoses required in operational practice. Our results further show that path restoration is generally more resource expensive, yet larger resource usage does not necessarily translate into better diagnosis.

cs.AI↗

arXiv2026

Physics-Aware Conditional SetGAN for Spatially Consistent Multi-User TR 38.901 Channel Generation

TR 38.901-based channel models such as Sionna are reliable, but generating many multi-user channel realizations remains expensive. This paper asks a practical question: can a trained generative model produce multi-user TR 38.901 channels faster than Sionna without losing the spatial correlations imposed by user geometry? To answer this question, we propose a physics-aware, geometry-conditioned SetGAN trained on Sionna reference data. The method separates large-scale received power from normalized small-scale fading, compresses the latter with principal component analysis, and learns the conditional channel distribution in a latent space while preserving geometry-dependent correlations. On the UMa/NLoS benchmark, the model keeps the received-power distributions close to the reference, with about 0.41 dB Wasserstein distance, and reproduces spatial-consistency profiles with mean deviations below 0.03 on median curves versus distance. In addition, it reduces elapsed generation time by a factor of 3.45 and CPU-total cost by a factor of 6.15 relative to Sionna under matched user positions in the fixed-position CPU-vs-CPU benchmark. These results show that a trained generative model can substantially accelerate TR 38.901 channel generation without breaking the spatial consistency needed to evaluate multi-user systems.

cs.LG↗

arXiv2026

HAPS as a Hypercell: Enabling Coverage and Capacity Carrier Shutdown in Cellular Networks

Energy consumption remains a dominant operational challenge for current and future cellular systems, especially in dense urban deployments. This paper investigates a novel role for non terrestrial network (NTN) high-altitude platform station (HAPS) as an enabler of energy-efficient operation rather than only coverage extension. We define the HAPS-Hypercell as a wide-area non-terrestrial layer that can assume the coverage role of multiple terrestrial macro-cells, enabling, for the first time, the shutdown of both capacity and coverage macro-cells. We develop a comprehensive third generation partnership project (3GPP)-compliant system model, along with two HAPS-Hypercell pairing architectures that capture the interplay among multiple layers, realistic channel conditions, and distributed carrier shutdown (CS) mechanisms. Our results show that the HAPS-Hypercell can effectively reduce overall network power consumption. We then identify key limitations of a straightforward HAPS integration, laying the groundwork for future optimization and providing key insights for next-generation CS operations.

cs.IT↗

arXiv2026

HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime

We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contain more responses with negative advantages than those with positive advantages, while response-level length normalization ties the magnitude of the update to the length of the output. We propose Hysteretic Policy Optimization (HPO), a minimal modification of GRPO that reduces the weight of negative-advantage updates and replaces per-response length normalization with mean-length normalization. We further introduce Adaptive HPO (A-HPO), which sets the hysteretic weight based on batch-level advantage-sign statistics, thereby removing the need for tuning a fixed hysteretic weight. In our TeleLogs and Countdown experiments, A-HPO improves the reward per update compared to GRPO, with the largest gains in early sparse reward regimes. On TeleLogs, A-HPO achieves a final reward of 0.84, outperforming SAPO by 5%, GSPO by 11%, and GRPO by 15%, while maintaining a comparable response-length. On Countdown, A-HPO achieves the largest gains in initial and most difficult configurations across 1.5B-7B models. Ablation studies on the hysteretic weight show that the gains of A-HPO come from better balancing the contributions of positive and negative advantages compared to positive-only or fully symmetric updates.

cs.LG↗

arXiv2026

Capacity and Energy Trade-Offs in FR3 6G Networks Using Real Deployment Data

This article presents a data-driven system-level analysis of multi-layer 6G networks operating in the upper mid-band (FR3: 7-24 GHz). Unlike most prior studies based on 3rd Generation Partnership Project (3GPP) templates, we leverage real-world deployment and traffic data from a commercial 4G/5G network in China to evaluate practical 6G strategies. Using Giulia-a deployment-informed system-level heterogeneous network model-we show that 6G can boost median throughput by up to 9.5x over heterogeneous 4G+5G deployments, but also increases power usage by up to 59%. Critically, co-locating 6G with existing sites delivers limited gains while incurring high energy cost. In contrast, non-co-located, traffic-aware deployments achieve superior throughput-to-watt efficiency, highlighting the need for strategic, user equipment (UE) hotspot-focused 6G planning.

cs.NI↗

arXiv2025

TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation

Large Language Models (LLMs) are increasingly applied to telecom engineering tasks, yet perform poorly on 3GPP specifications. These standards encode much of their technical information in complex tables, but LLM knowledge and interpretation of such tables remain largely unexplored. We introduce TeleTables, a benchmark comprising 2,220 tables from 13 3GPP specifications in four formats and 500 human-verified MCQs spanning direct retrieval to multi-step reasoning. Evaluating 20 open-weight LLMs across non reasoning, multimodal, reasoning, and table specialized architectures reveals two distinct performance bottlenecks. In the closed-book setting, domain knowledge is the primary constraint, with no general-purpose model exceeding 41% accuracy. When the table is provided as context, the best models exceed 90%, but performance degrades systematically with reasoning depth, evidence scope, and structural complexity, with a 32.2pp spread across reasoning skills. Table specialization on non-telecom data provides no consistent benefit, while strong reasoning capabilities remain essential for reliable interpretation of complex technical tables.

cs.CL↗

arXiv2025

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache compression methods either enforce rigid heuristics, disrupt tensor layouts with per-attention-head variability, or require specialized compute kernels. We propose a simple, yet effective, KV cache compression framework based on attention-guided, layer-adaptive composite tokens. Our method aggregates attention scores to estimate token importance, selects head-specific tokens independently, and aligns them into composite tokens that respect the uniform cache structure required by existing inference engines. A global allocation mechanism further adapts retention budgets across layers, assigning more capacity to layers with informative tokens. This approach achieves significant memory reduction while preserving accuracy, consistently outperforming prior structured and semi-structured methods. Crucially, our approach remains fully compatible with standard inference pipelines, offering a practical and scalable solution for efficient long-context LLM deployment.

cs.LG↗

arXiv2025

Reasoning Language Models for Root Cause Analysis in 5G Wireless Networks

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.

cs.AI↗

arXiv2025

TeleMath: A Benchmark for Large Language Models in Telecom Mathematical Problem Solving

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.

cs.AI↗

arXiv2025

Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing

Artificial intelligence will be one of the key pillars of the next generation of mobile networks (6G), as it is expected to provide novel added-value services and improve network performance. In this context, large language models have the potential to revolutionize the telecom landscape through intent comprehension, intelligent knowledge retrieval, coding proficiency, and cross-domain orchestration capabilities. This paper presents Telco-oRAG, an open-source Retrieval-Augmented Generation (RAG) framework optimized for answering technical questions in the telecommunications domain, with a particular focus on 3GPP standards. Telco-oRAG introduces a hybrid retrieval strategy that combines 3GPP domain-specific retrieval with web search, supported by glossary-enhanced query refinement and a neural router for memory-efficient retrieval. Our results show that Telco-oRAG improves the accuracy in answering 3GPP-related questions by up to 17.6% and achieves a 10.6% improvement in lexicon queries compared to baselines. Furthermore, Telco-oRAG reduces memory usage by 45% through targeted retrieval of relevant 3GPP series compared to baseline RAG, and enables open-source LLMs to reach GPT-4-level accuracy on telecom benchmarks.

cs.IR↗

arXiv2025

Goal-Oriented Time-Series Forecasting: Foundation Framework Design

Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downstream applications. We propose a training methodology that enables forecasting models to adapt their focus to application-specific regions of interest at inference time, without retraining. The approach partitions the prediction space into fine-grained segments during training, which are dynamically reweighted and aggregated to emphasize the target range specified by the application. Unlike prior methods that predefine these ranges, our framework supports flexible, on-demand adjustments. Experiments on standard benchmarks and a newly collected wireless communication dataset demonstrate that our method not only improves forecast accuracy within regions of interest but also yields measurable gains in downstream task performance. These results highlight the potential for closer integration between predictive modeling and decision-making in real-world systems.

cs.LG↗

arXiv2024

Capacity and Power Consumption of Multi-Layer 6G Networks Using the Upper Mid-Band

This paper presents a new system model to evaluate the capacity and power consumption of multi-layer 6G networks utilising the upper mid-band (FR3). The model captures heterogeneous 4G, 5G, and 6G deployments, analyzing their performance under different deployment strategies. Our results show that strategic 6G deployments, non-co-located with existing 5G sites, significantly enhance throughput, with median and peak user rates of 300 Mbps and exceeding 1 Gbps, respectively. We also emphasize the importance of priority-based cell reselection and beam configuration to fully leverage 6G capabilities. While 6G implementation increases power consumption by 33%, non-colocated deployments strike a balance between performance and power consumption.

cs.NI↗

arXiv2024

Hermes: A Large Language Model Framework on the Journey to Autonomous Networks

The drive toward automating cellular network operations has grown with the increasing complexity of these systems. Despite advancements, full autonomy currently remains out of reach due to reliance on human intervention for modeling network behaviors and defining policies to meet target requirements. Network Digital Twins (NDTs) have shown promise in enhancing network intelligence, but the successful implementation of this technology is constrained by use case-specific architectures, limiting its role in advancing network autonomy. A more capable network intelligence, or "telecommunications brain", is needed to enable seamless, autonomous management of cellular network. Large Language Models (LLMs) have emerged as potential enablers for this vision but face challenges in network modeling, especially in reasoning and handling diverse data types. To address these gaps, we introduce Hermes, a chain of LLM agents that uses "blueprints" for constructing NDT instances through structured and explainable logical steps. Hermes allows automatic, reliable, and accurate network modeling of diverse use cases and configurations, thus marking progress toward fully autonomous network operations.

cs.AI↗

arXiv2024

Optimal SSB Beam Planning and UAV Cell Selection for 5G Connectivity on Aerial Highways

In this article, we introduce a method to optimize 5G massive multiple-input multiple-output (mMIMO) connectivity for unmanned aerial vehicles (UAVs) on aerial highways through strategic cell association. UAVs operating in 3D space encounter distinct channel conditions compared to traditional ground user equipment (gUE); under the typical line of sight (LoS) condition, UAVs perceive strong reference signal received power (RSRP) from multiple cells within the network, resulting in a large set of suitable serving cell candidates and in low signal-to-interference-plus-noise ratio (SINR) due to high interference levels. Additionally, a downside of aerial highways is to pack possibly many UAVs along a small portion of space which, when taking into account typical LoS propagation conditions, results in high channel correlation and severely limits spatial multiplexing capabilities. In this paper, we propose a solution to both problems based on the suitable selection of serving cells based on a new metric which differs from the classical terrestrial approaches based on maximum RSRP. We then introduce an algorithm for optimal planning of synchronization signal block (SSB) beams for this set of cells, ensuring maximum coverage and effective management of UAVs cell associations. Simulation results demonstrate that our approach significantly improves the rates of UAVs on aerial highways, up to four times in achievable data rates, without impacting ground user performance.

cs.IT↗

arXiv2024

Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for Telecommunications

The application of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems in the telecommunication domain presents unique challenges, primarily due to the complex nature of telecom standard documents and the rapid evolution of the field. The paper introduces Telco-RAG, an open-source RAG framework designed to handle the specific needs of telecommunications standards, particularly 3rd Generation Partnership Project (3GPP) documents. Telco-RAG addresses the critical challenges of implementing a RAG pipeline on highly technical content, paving the way for applying LLMs in telecommunications and offering guidelines for RAG implementation in other technical domains.

cs.IR↗

arXiv2024

Waste Factor and Waste Figure: A Unified Theory for Modeling and Analyzing Wasted Power in Radio Access Networks for Improved Sustainability

This paper introduces Waste Factor (W), also denoted as Waste Figure (WF) in dB, a promising new metric for quantifying energy efficiency in a wide range of circuits and systems applications, including data centers and RANs. Also, the networks used to connect data centers and AI computing engines with users for ML applications must become more power efficient. This paper illustrates the limitations of existing energy efficiency metrics that inadequately capture the intricate energy dynamics of RAN components. We delineate the methodology for applying W across various network configurations, including MISO, SIMO, and MIMO systems, and demonstrate the effectiveness of W in identifying energy optimization opportunities. Our findings reveal that W not only offers nuanced insights into the energy performance of RANs but also facilitates informed decision-making for network design and operational efficiency. Furthermore, we show how W can be integrated with other KPIs to guide the development of optimal strategies for enhancing network energy efficiency under different operational conditions. Additionally, we present simulation results for a distributed multi-user MIMO system at 3.5, 17, and 28 GHz, demonstrating overall network power efficiency on a per square kilometer basis, and show how overall W decreases with an increasing number of base stations and increasing carrier frequency. This paper shows that adopting W as a figure of merit can significantly contribute to the sustainability and energy optimization of next-generation wireless communication networks, paving the way for greener and more sustainable, energy-efficient 5G and 6G technologies.

cs.NI↗

arXiv2024

Telecom Language Models: Must They Be Large?

The increasing interest in Large Language Models (LLMs) within the telecommunications sector underscores their potential to revolutionize operational efficiency. However, the deployment of these sophisticated models is often hampered by their substantial size and computational demands, raising concerns about their viability in resource-constrained environments. Addressing this challenge, recent advancements have seen the emergence of small language models that surprisingly exhibit performance comparable to their larger counterparts in many tasks, such as coding and common-sense reasoning. Phi-2, a compact yet powerful model, exemplifies this new wave of efficient small language models. This paper conducts a comprehensive evaluation of Phi-2's intrinsic understanding of the telecommunications domain. Recognizing the scale-related limitations, we enhance Phi-2's capabilities through a Retrieval-Augmented Generation approach, meticulously integrating an extensive knowledge base specifically curated with telecom standard specifications. The enhanced Phi-2 model demonstrates a profound improvement in accuracy, answering questions about telecom standards with a precision that closely rivals the more resource-intensive GPT-3.5. The paper further explores the refined capabilities of Phi-2 in addressing problem-solving scenarios within the telecom sector, highlighting its potential and limitations.

cs.CL↗

arXiv2024

Modelling the 5G Energy Consumption using Real-world Data: Energy Fingerprint is All You Need

The introduction of 5G technology has revolutionized communications, enabling unprecedented capacity, connectivity, and ultra-fast, reliable communications. However, this leap has led to a substantial increase in energy consumption, presenting a critical challenge for network sustainability. Accurate energy consumption modeling is essential for developing energy-efficient strategies, enabling operators to optimize resource utilization while maintaining network performance. To address this, we propose a novel deep learning model for 5G base station energy consumption estimation based on a real-world dataset. Unlike existing methods, our approach integrates the Base Station Identifier (BSID) as an input feature through an embedding layer, capturing unique energy patterns across different base stations. We further introduce a masked training method and an attention mechanism to enhance generalization and accuracy. Experimental results show significant improvements, reducing Mean Absolute Percentage Error (MAPE) from 12.75% to 4.98%, achieving over 60% performance gain compared to existing models. The source code for our model is available at https://github.com/RS2002/ARL.

eess.SP↗