2026· IEEE Open Journal of the Communications Society· Vol 7, pp. 9128-9144· 0 citations· 31 references
TL;DR
Reflex-Core is proposed, an LLM-agent-based framework for AoI-oriented adaptive access in heterogeneous wireless networks that adopts an “Observe-Reflect-Decide-Execute” closed-loop mechanism to refine transmission strategies through semantic feedback and historical memory and develops the Reflexive Multiple Access protocol and a priority-aware RMA variant for differentiated freshness requirements.
Abstract
With the rapid expansion of the Internet of Things (IoT) and heterogeneous wireless networks, Age of Information (AoI) has emerged as a critical metric for evaluating information freshness in real-time systems. AoI-oriented access optimization in heterogeneous multiple access networks is challenging because legacy access mechanisms, such as TDMA and ALOHA, may coexist over a shared channel, while conventional rule-based and learning-based methods often suffer from limited adaptability, slow convergence, and poor interpretability. In this paper, we propose Reflex-Core, an LLM-agent-based framework for AoI-oriented adaptive access in heterogeneous wireless networks. Reflex-Core adopts an “Observe-Reflect-Decide-Execute” closed-loop mechanism to refine transmission strategies through semantic feedback and historical memory. To provide an analytical foundation for reflection-guided strategy refinement, we derive a drift-plus-penalty design principle and construct a reflection-cycle-level reward target that jointly captures weighted AoI reduction and collision cost. This reward target guides reflection selection, reward model training, and PPO-based post-training. Based on Reflex-Core, we develop the Reflexive Multiple Access (RMA) protocol and a priority-aware RMA variant for differentiated freshness requirements. We further discuss an asynchronous edge-assisted implementation, where LLM-based reflection can be offloaded without blocking slot-level random access. Simulation results show that RMA reduces AoI by up to 14.9% compared with representative baselines and maintains robust performance in dynamic and priority-aware scenarios. Additional scalability and backbone-sensitivity experiments further confirm that Reflex-Core remains effective in a 20-node heterogeneous scenario with varied ALOHA loads and is robust when LongChat-7B-16k is replaced by Qwen2.5-7B-Instruct.
This paper introduces an embodied agentic AI framework that integrates large language models (LLMs) with multi-agent reinforcement learning (MADRL) to enable adaptive control in cognitive satellite-terrestrial networks (CSTNs). The framework embeds LLM-based cognitive modules into network entities, transforming them into autonomous agents capable of semantic perception, reasoning, and collaborative decision-making. To address key CSTN challenges such as dynamic interference, complex resource allocation, and heterogeneous quality-of-service (QoS) demands, we employ LLMs to interpret high-level operational intents, augmented by retrieval-augmented generation (RAG) for accessing domain knowledge. This enables each agent to adaptively configure rate-splitting multiple access (RSMA)-based protocols, derive key performance metrics (e.g., outage probability, age of information), and formulate a constrained long-term energy efficiency optimization problem. To solve this problem, we propose an LLM-enhanced multi-agent proximal policy optimization (LEMAPPO) algorithm for joint power and rate allocation. The LLM enhances MAPPO through action guidance and reward function design, thereby improving learning efficiency and policy robustness. Simulations demonstrate that the proposed algorithm achieves substantial energy efficiency gains while satisfying reliability and timeliness constraints, outperforming existing benchmarks. Specifically, it outperforms standard MAPPO by up to 28.5% in energy efficiency under stringent outage constraints, and achieves 27.3% higher efficiency than MAPPO in multi-user scenarios.
Chenbo Hu, Hongjuan Yang, Bo Li et al.· IEEE Transactions on Cogniti...· 0 citations
The main conclusion is that practical Agentic IoT depends less on placing an entire agent at one tier than on partitioning perception, memory, reasoning, and action under explicit latency, privacy, reliability, and safety constraints.
The rapid proliferation of Internet of Things (IoT) devices has placed unprecedented pressure on the network edge, where applications such as augmented reality, real-time analytics, and autonomous navigation demand low latency and tight energy budgets that traditional cloud-centric architectures cannot meet. Multi-access Edge Computing (MEC) addresses this gap by relocating computation closer to end users, but the core question of where and how each task should be executed remains open: rulebased and single-objective offloading strategies fail to simultaneously balance service latency, energy efficiency, and user experience under dynamic, large-scale conditions. In this paper we propose TARLOT (Two-Agent Reinforcement Learning Offloading Tasks), a cooperative framework for threetier IoT–MEC–Cloud environments. TARLOT decouples the offloading decision from the resourceallocation problem and assigns each to a dedicated Q-learning agent, so that the two subproblems are specialised independently while still being optimised jointly. The framework is evaluated on PureEdgeSim under heterogeneous IoT workloads, device densities ranging from 200 to 2,400, and diverse application profiles, and is compared against five widely-used baselines (Random, Round-Robin, Trade-Off, Pure-Edge, and Pure-Cloud). At 2,400 devices, TARLOT delivers an average service time of 1.1 s (against 4.3 s for Pure-Cloud), a Quality of Experience of 0.77 (against 0.22 for Pure-Cloud), a task-failure rate below 2 % (against nearly 14 % for Pure-Cloud), and a per-device energy consumption of only 3.6 W (against 11.2 W for Pure-Cloud) — roughly a 68 % reduction. Balanced CPU utilisation across the local, edge, and cloud tiers further confirms that TARLOT prevents resource bottlenecks, establishing it as a practical solution for next-generation large-scale IoT deployments.
Oussama Lagnfdi, Marouane Myyara, A. Darif· International journal of Com...· 0 citations
Comparative results show that WARA substantially outperforms one-shot LLM generation and approaches the quality profile of recently accepted peer-reviewed papers, demonstrating the potential of closed-loop artifact control for end-to-end LLM-assisted wireless optimization research.
Yuan-Cheng Guo, Yilong Chen, Chao Hu et al.· 1 citation· ⚡1
Communication bottlenecks remain a primary obstacle to the large-scale deployment of federated learning (FL). This article proposes a comprehensive framework for building communication-efficient FL, founded on three fundamental pillars: model compression, client selection, and resource allocation. We first survey state-of-the-art techniques for each pillar, specifically elucidating how quantization, pruning, and low-rank approximation reduce payloads; how intelligent client schedulers exploit heterogeneity; and how emerging communication paradigms such as Integrated Sensing and Communication (ISAC) and Over-the-Air Computation (AirComp) redefine bandwidth and energy utilization. Subsequently, these insights are unified through a task-oriented design philosophy that couples strategy selection with cross-layer, multi-objective optimization. To validate the proposed framework, we present an autonomous driving case study with two complementary experiments: a task-oriented client scheduling strategy that improves object detection accuracy under the same communication time budget, and a joint quantization-bandwidth optimization that further reduces total training time under dynamic networks. Together, the experiments demonstrate the advantages of holistic task-oriented design for real-world FL deployment.
Fu-Qiang Pan, Yan Liu, Er-Wu Liu et al.· 0 citations
Managing cloud infrastructure has become more challenging as the number of artificial intelligence (AI) workloads are increasing. In this regard, reactive, energy-inefficient, and uncooperative rule-based traditional orchestrations and single-agent reinforcement learning are ineffective. To address these issues, we propose in this paper a meta-optimized cooperative autonomous infrastructure (MOCAI) to enable predictive, self-managed, and trustworthy AI management. Our approach is based on prediction (using a temporal graph transformer), multi-agent meta-reinforcement learning, multi-agent negotiation (using games), trust-sized consensus, and explainable governance of decision-making. MOCAI is different from before, as it is a resource optimization system that predicts infrastructure behavior and cooperation of agents via cooperative intelligence. The system was tested in a cloud-edge system, which is 92.4 percent resource-efficient with 21 percent energy savings, 1.9 percent service level agreement (SLA) breach, and 95.6 percent secure. The performance of the prediction and cooperating negotiation strategies has been proven in the ablation studies. This research will take the autonomous infrastructure to the next level of scalable, secure, and sustainable artificial intelligence (AI) ecosystems, which can be used for the next generation of smart cloud ecosystems.
M.Kathiravan· 2026 4th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
