Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often overly simplistic, allowing models to perform uniformly well, making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs, which models might memorize or guess. To address these limitations, we introduce the Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying DIA-Bench dataset, which includes 150 diverse and challenging task templates with mutable parameters, is presented in various formats such as text, PDFs, compiled binaries, and visual puzzles. Our framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models' reliability. Notably, models like GPT-4o tended to overestimate their mathematical abilities, while ChatGPT-4o demonstrated better decision-making and performance through effective tool usage. We evaluated eight state-of-the-art large language models (LLMs) using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving but also a model's adaptive intelligence and ability to assess its own limitations. The dataset is publicly available on our project's website.

Large Language Model Based Multi-Objective Optimization for Integrated Sensing and Communications in UAV Networks

This letter investigates an unmanned aerial vehicle (UAV) network with integrated sensing and communication (ISAC) systems, where multiple UAVs simultaneously sense the locations of ground users and provide communication services with radars. To find the trade-off between communication and sensing (C\&S) in the system, we formulate a multi-objective optimization problem (MOP) to maximize the total network utility and the localization Cram\'er-Rao bounds (CRB) of ground users, which jointly optimizes the deployment and power control of UAVs. Inspired by the huge potential of large language models (LLM) for prediction and inference, we propose an LLM-enabled decomposition-based multi-objective evolutionary algorithm (LEDMA) for solving the highly non-convex MOP. We first adopt a decomposition-based scheme to decompose the MOP into a series of optimization sub-problems. We second integrate LLMs as black-box search operators with MOP-specifically designed prompt engineering into the framework of MOEA to solve optimization sub-problems simultaneously. Numerical results demonstrate that the proposed LEDMA can find the clear trade-off between C\&S and outperforms baseline MOEAs in terms of obtained Pareto fronts and convergence.

Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards

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.

Beyond Diagonal RIS: Passive Maximum Ratio Transmission and Interference Nulling Enabler

Beyond diagonal reconfigurable intelligent surfaces (BD-RIS) generalizes and goes beyond conventional diagonal reconfigurable intelligent surfaces (D-RIS) by interconnecting elements to generate beyond diagonal scattering matrices, which significantly strengthen the wireless channels. In this work, we use BD-RIS for passive multiuser beamforming in multiuser multiple-input-single-output (MU-MISO) systems. Specifically, we design the scattering matrix of BD-RIS to either maximize the sum received signal power at the users following maximum ratio transmission (MRT), or to nullify the interference at the users following zero forcing (ZF). Furthermore, we investigate uniform/optimized power allocation and ZF precoding at the base station (BS). Numerical results show that BD-RIS improves the interference nulling capability and sum rate with fewer reflecting elements (REs) compared to D-RIS. In addition, at moderate to high signal to noise ratios (SNRs), passive interference nulling reduces the complexity at the BS by relaxing the need for precoding or water-filling power allocation design. Furthermore, the passive MRT with ZF precoding achieves a tight sum rate performance to the joint design considering MU-MISO scenarios with many REs while maintaining low computational complexity and simplifying the channel estimation.

Transforming Time-Varying to Static Channels: The Power of Fluid Antenna Mobility

This paper addresses the mobility problem with the assistance of fluid antenna (FA) on the user equipment (UE) side. We propose a matrix pencil-based moving port (MPMP) prediction method, which may transform the time-varying channel to a static channel by timely sliding the liquid. Different from the existing channel prediction method, we design a moving port selection method, which is the first attempt to transform the channel prediction to the port prediction by exploiting the movability of FA. Theoretical analysis shows that for the line-ofsight (LoS) channel, the prediction error of our proposed MPMP method may converge to zero, as the number of BS antennas and the port density of the FA are large enough. For a multi-path channel, we also derive the upper and lower bounds of the prediction error when the number of paths is large enough. When the UEs move at a speed of 60 or 120 km/h, simulation results show that, with the assistance of FA, our proposed MPMP method performs better than the existing channel prediction method.

TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models

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.

Generative AI for RF Sensing in IoT systems

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.

RIS-assisted Coverage Enhancement in mmWave Integrated Sensing and Communication Networks

Integrated sensing and communication (ISAC) has emerged as a promising technology to facilitate high-rate communications and super-resolution sensing, particularly operating in the millimeter wave (mmWave) band. However, the vulnerability of mmWave signals to blockages severely impairs ISAC capabilities and coverage. To tackle this, an efficient and low-cost solution is to deploy distributed reconfigurable intelligent surfaces (RISs) to construct virtual links between the base stations (BSs) and users in a controllable fashion. In this paper, we investigate the generalized RIS-assisted mmWave ISAC networks considering the blockage effect, and examine the beneficial impact of RISs on the coverage rate utilizing stochastic geometry. Specifically, taking into account the coupling effect of ISAC dual functions within the same network topology, we derive the conditional coverage probability of ISAC performance for two association cases, based on the proposed beam pattern model and user association policies. Then, the marginal coverage rate is calculated by combining these two cases through the distance-dependent thinning method. Simulation results verify the accuracy of derived theoretical formulations and provide valuable guidelines for the practical network deployment. Specifically, our results indicate the superiority of the RIS deployment with the density of 40 km${}^{-2}$ BSs, and that the joint coverage rate of ISAC performance exhibits potential growth from $67.1\%$ to $92.2\%$ with the deployment of RISs.

Flexible Antenna Arrays for Wireless Communications: Modeling and Performance Evaluation

Flexible antenna arrays (FAAs), distinguished by their rotatable, bendable, and foldable properties, are extensively employed in flexible radio systems to achieve customized radiation patterns. This paper aims to illustrate that FAAs, capable of dynamically adjusting surface shapes, can enhance communication performances with both omni-directional and directional antenna patterns, in terms of multi-path channel power and channel angle Cram\'{e}r-Rao bounds. To this end, we develop a mathematical model that elucidates the impacts of the variations in antenna positions and orientations as the array transitions from a flat to a rotated, bent, and folded state, all contingent on the flexible degree-of-freedom. Moreover, since the array shape adjustment operates across the entire beamspace, especially with directional patterns, we discuss the sum-rate in the multi-sector base station that covers the $360^\circ$ communication area. Particularly, to thoroughly explore the multi-sector sum-rate, we propose separate flexible precoding (SFP), joint flexible precoding (JFP), and semi-joint flexible precoding (SJFP), respectively. In our numerical analysis comparing the optimized FAA to the fixed uniform planar array, we find that the bendable FAA achieves a remarkable $156\%$ sum-rate improvement compared to the fixed planar array in the case of JFP with the directional pattern. Furthermore, the rotatable FAA exhibits notably superior performance in SFP and SJFP cases with omni-directional patterns, with respective $35\%$ and $281\%$.

Large Language Models for Power Scheduling: A User-Centric Approach

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.