The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still lacks a comprehensive benchmark to systematically assess the effect of each distillation approach. This paper introduces DC-CoT, the first data-centric benchmark that investigates data manipulation in chain-of-thought (CoT) distillation from method, model and data perspectives. Utilizing various teacher models (e.g., o4-mini, Gemini-Pro, Claude-3.5) and student architectures (e.g., 3B, 7B parameters), we rigorously evaluate the impact of these data manipulations on student model performance across multiple reasoning datasets, with a focus on in-distribution (IID) and out-of-distribution (OOD) generalization, and cross-domain transfer. Our findings aim to provide actionable insights and establish best practices for optimizing CoT distillation through data-centric techniques, ultimately facilitating the development of more accessible and capable reasoning models. The dataset can be found at https://huggingface.co/datasets/rana-shahroz/DC-COT, while our code is shared in https://anonymous.4open.science/r/DC-COT-FF4C/.

Temporal Spectrum Cartography in Low-Altitude Economy Networks: A Generative AI Framework with Multi-Agent Learning

This paper introduces a two-stage generative AI (GenAI) framework tailored for temporal spectrum cartography in low-altitude economy networks (LAENets). LAENets, characterized by diverse aerial devices such as UAVs, rely heavily on wireless communication technologies while facing challenges, including spectrum congestion and dynamic environmental interference. Traditional spectrum cartography methods have limitations in handling the temporal and spatial complexities inherent to these networks. Addressing these challenges, the proposed framework first employs a Reconstructive Masked Autoencoder (RecMAE) capable of accurately reconstructing spectrum maps from sparse and temporally varying sensor data using a novel dual-mask mechanism. This approach significantly enhances the precision of reconstructed radio frequency (RF) power maps. In the second stage, the Multi-agent Diffusion Policy (MADP) method integrates diffusion-based reinforcement learning to optimize the trajectories of dynamic UAV sensors. By leveraging temporal-attention encoding, this method effectively manages spatial exploration and exploitation to minimize cumulative reconstruction errors. Extensive numerical experiments validate that this integrated GenAI framework outperforms traditional interpolation methods and deep learning baselines by achieving 57.35% and 88.68% reconstruction error reduction, respectively. The proposed trajectory planner substantially improves spectrum map accuracy, reconstruction stability, and sensor deployment efficiency in dynamically evolving low-altitude environments.

LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach

Nowadays, Generative AI (GenAI) reshapes numerous domains by enabling machines to create content across modalities. As GenAI evolves into autonomous agents capable of reasoning, collaboration, and interaction, they are increasingly deployed on network infrastructures to serve humans automatically. This emerging paradigm, known as the agentic network, presents new optimization challenges due to the demand to incorporate subjective intents of human users expressed in natural language. Traditional generic Deep Reinforcement Learning (DRL) struggles to capture intent semantics and adjust policies dynamically, thus leading to suboptimality. In this paper, we present LAMeTA, a Large AI Model (LAM)-empowered Two-stage Approach for intent-aware agentic network optimization. First, we propose Intent-oriented Knowledge Distillation (IoKD), which efficiently distills intent-understanding capabilities from resource-intensive LAMs to lightweight edge LAMs (E-LAMs) to serve end users. Second, we develop Symbiotic Reinforcement Learning (SRL), integrating E-LAMs with a policy-based DRL framework. In SRL, E-LAMs translate natural language user intents into structured preference vectors that guide both state representation and reward design. The DRL, in turn, optimizes the generative service function chain composition and E-LAM selection based on real-time network conditions, thus optimizing the subjective Quality-of-Experience (QoE). Extensive experiments conducted in an agentic network with 81 agents demonstrate that IoKD reduces mean squared error in intent prediction by up to 22.5%, while SRL outperforms conventional generic DRL by up to 23.5% in maximizing intent-aware QoE.

LLM-guided DRL for Multi-tier LEO Satellite Networks with Hybrid FSO/RF Links

Despite significant advancements in terrestrial networks, inherent limitations persist in providing reliable coverage to remote areas and maintaining resilience during natural disasters. Multi-tier networks with low Earth orbit (LEO) satellites and high-altitude platforms (HAPs) offer promising solutions, but face challenges from high mobility and dynamic channel conditions that cause unstable connections and frequent handovers. In this paper, we design a three-tier network architecture that integrates LEO satellites, HAPs, and ground terminals with hybrid free-space optical (FSO) and radio frequency (RF) links to maximize coverage while maintaining connectivity reliability. This hybrid approach leverages the high bandwidth of FSO for satellite-to-HAP links and the weather resilience of RF for HAP-to-ground links. We formulate a joint optimization problem to simultaneously balance downlink transmission rate and handover frequency by optimizing network configuration and satellite handover decisions. The problem is highly dynamic and non-convex with time-coupled constraints. To address these challenges, we propose a novel large language model (LLM)-guided truncated quantile critics algorithm with dynamic action masking (LTQC-DAM) that utilizes dynamic action masking to eliminate unnecessary exploration and employs LLMs to adaptively tune hyperparameters. Simulation results demonstrate that the proposed LTQC-DAM algorithm outperforms baseline algorithms in terms of convergence, downlink transmission rate, and handover frequency. We also reveal that compared to other state-of-the-art LLMs, DeepSeek delivers the best performance through gradual, contextually-aware parameter adjustments.

Shadow Wireless Intelligence: Large Language Model-Driven Reasoning in Covert Communications

Covert Communications (CC) can secure sensitive transmissions in industrial, military, and mission-critical applications within 6G wireless networks. However, traditional optimization methods based on Artificial Noise (AN), power control, and channel manipulation might not adapt to dynamic and adversarial environments due to the high dimensionality, nonlinearity, and stringent real-time covertness requirements. To bridge this gap, we introduce Shadow Wireless Intelligence (SWI), which integrates the reasoning capabilities of Large Language Models (LLMs) with retrieval-augmented generation to enable intelligent decision-making in covert wireless systems. Specifically, we utilize DeepSeek-R1, a mixture-of-experts-based LLM with RL-enhanced reasoning, combined with real-time retrieval of domain-specific knowledge to improve context accuracy and mitigate hallucinations. Our approach develops a structured CC knowledge base, supports context-aware retrieval, and performs semantic optimization, allowing LLMs to generate and adapt CC strategies in real time. In a case study on optimizing AN power in a full-duplex CC scenario, DeepSeek-R1 achieves 85% symbolic derivation accuracy and 94% correctness in the generation of simulation code, outperforming baseline models. These results validate SWI as a robust, interpretable, and adaptive foundation for LLM-driven intelligent covert wireless systems in 6G networks.

Enabling Training-Free Semantic Communication Systems with Generative Diffusion Models

Semantic communication (SemCom) has recently emerged as a promising paradigm for next-generation wireless systems. Empowered by advanced artificial intelligence (AI) technologies, SemCom has achieved significant improvements in transmission quality and efficiency. However, existing SemCom systems either rely on training over large datasets and specific channel conditions or suffer from performance degradation under channel noise when operating in a training-free manner. To address these issues, we explore the use of generative diffusion models (GDMs) as training-free SemCom systems. Specifically, we design a semantic encoding and decoding method based on the inversion and sampling process of the denoising diffusion implicit model (DDIM), which introduces a two-stage forward diffusion process, split between the transmitter and receiver to enhance robustness against channel noise. Moreover, we optimize sampling steps to compensate for the increased noise level caused by channel noise. We also conduct a brief analysis to provide insights about this design. Simulations on the Kodak dataset validate that the proposed system outperforms the existing baseline SemCom systems across various metrics.

Decentralization of Generative AI via Mixture of Experts for Wireless Networks: A Comprehensive Survey

Mixture of Experts (MoE) has emerged as a promising paradigm for scaling model capacity while preserving computational efficiency, particularly in large-scale machine learning architectures such as large language models (LLMs). Recent advances in MoE have facilitated its adoption in wireless networks to address the increasing complexity and heterogeneity of modern communication systems. This paper presents a comprehensive survey of the MoE framework in wireless networks, highlighting its potential in optimizing resource efficiency, improving scalability, and enhancing adaptability across diverse network tasks. We first introduce the fundamental concepts of MoE, including various gating mechanisms and the integration with generative AI (GenAI) and reinforcement learning (RL). Subsequently, we discuss the extensive applications of MoE across critical wireless communication scenarios, such as vehicular networks, unmanned aerial vehicles (UAVs), satellite communications, heterogeneous networks, integrated sensing and communication (ISAC), and mobile edge networks. Furthermore, key applications in channel prediction, physical layer signal processing, radio resource management, network optimization, and security are thoroughly examined. Additionally, we present a detailed overview of open-source datasets that are widely used in MoE-based models to support diverse machine learning tasks. Finally, this survey identifies crucial future research directions for MoE, emphasizing the importance of advanced training techniques, resource-aware gating strategies, and deeper integration with emerging 6G technologies.

Aerial Active STAR-RIS-assisted Satellite-Terrestrial Covert Communications

An integration of satellites and terrestrial networks is crucial for enhancing performance of next generation communication systems. However, the networks are hindered by the long-distance path loss and security risks in dense urban environments. In this work, we propose a satellite-terrestrial covert communication system assisted by the aerial active simultaneous transmitting and reflecting reconfigurable intelligent surface (AASTAR-RIS) to improve the channel capacity while ensuring the transmission covertness. Specifically, we first derive the minimal detection error probability (DEP) under the worst condition that the Warden has perfect channel state information (CSI). Then, we formulate an AASTAR-RIS-assisted satellite-terrestrial covert communication optimization problem (ASCCOP) to maximize the sum of the fair channel capacity for all ground users while meeting the strict covert constraint, by jointly optimizing the trajectory and active beamforming of the AASTAR-RIS. Due to the challenges posed by the complex and high-dimensional state-action spaces as well as the need for efficient exploration in dynamic environments, we propose a generative deterministic policy gradient (GDPG) algorithm, which is a generative deep reinforcement learning (DRL) method to solve the ASCCOP. Concretely, the generative diffusion model (GDM) is utilized as the policy representation of the algorithm to enhance the exploration process by generating diverse and high-quality samples through a series of denoising steps. Moreover, we incorporate an action gradient mechanism to accomplish the policy improvement of the algorithm, which refines the better state-action pairs through the gradient ascent. Simulation results demonstrate that the proposed approach significantly outperforms important benchmarks.

Towards Secure Semantic Communications in the Presence of Intelligent Eavesdroppers

Semantic communication has emerged as a promising paradigm for enhancing communication efficiency in sixth-generation (6G) networks. However, the broadcast nature of wireless channels makes SemCom systems vulnerable to eavesdropping, which poses a serious threat to data privacy. Therefore, we investigate secure SemCom systems that preserve data privacy in the presence of eavesdroppers. Specifically, we first explore a scenario where eavesdroppers are intelligent and can exploit semantic information to reconstruct the transmitted data based on advanced artificial intelligence (AI) techniques. To counter this, we introduce novel eavesdropping attack strategies that utilize model inversion attacks and generative AI (GenAI) models. These strategies effectively reconstruct transmitted private data processed by the semantic encoder, operating in both glass-box and closed-box settings. Existing defense mechanisms against eavesdropping often cause significant distortions in the data reconstructed by eavesdroppers, potentially arousing their suspicion. To address this, we propose a semantic covert communication approach that leverages an invertible neural network (INN)-based signal steganography module. This module covertly embeds the channel input signal of a private sample into that of a non-sensitive host sample, thereby misleading eavesdroppers. Without access to this module, eavesdroppers can only extract host-related information and remain unaware of the hidden private content. We conduct extensive simulations under various channel conditions in image transmission tasks. Numerical results show that while conventional eavesdropping strategies achieve a success rate of over 80\% in reconstructing private information, the proposed semantic covert communication effectively reduces the eavesdropping success rate to 0.

Movable Cell-Free Massive MIMO For High-Speed Train Communications: A PPO-Based Antenna Position Optimization

In recent years, high-speed trains (HSTs) communications have developed rapidly to enhance the stability of train operations and improve passenger connectivity experiences. However, as the train continues to accelerate, urgent technological innovations are needed to overcome challenges such as frequency handover and significant Doppler effects. In this paper, we present a novel architecture featuring movable antennas (MAs) to fully exploit macro spatial diversity, enabling a cell-free (CF) massive multiple-input multiple-output (MIMO) system that supports high-speed train communications. Considering the high likelihood of line-of-sight (LoS) transmission in HST scenario, we derive the uplink spectral efficiency (SE) expression for the movable CF massive MIMO system. Moreover, an optimization problem is formulated to maximize the sum SE of the considered system by optimizing the positions of the antennas. Since the formulated problem is non-convex and highly non-linear, we improve a deep reinforcement learning algorithm to address it by using proximal policy optimization (PPO). Different from traditional optimization approaches, which optimize variables separately and alternately, our improved PPO-based approach optimizes all the variables in unison. Simulation results demonstrate that movable CF massive MIMO effectively suppresses the negative impact of the Doppler effect in HST communications.