Yuqing Cao, Xiliang Chen^*, Legui Zhang^*, Jun Lai, Haoyang Dong, Xuefei Sun, Xiaoyan Wang

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.086261 - 13 August 2026

Abstract The design of reward functions is crucial to the success of reinforcement learning, yet the process often relies on expert experience and is difficult to debug. Although large language models (LLMs) offer new opportunities for automated reward design, existing methods still face challenges such as poor interpretability, inability to reuse knowledge, and optimization blindness. To address these issues, this paper proposes a method for structural decoupling and knowledge reuse evolution, referred to as SD-KRE. Its core lies in treating the reward function as a composition of multiple structured units with clear semantics and functionally decoupled… More >

Huayu Li¹, Xiang Wang¹, Jia Luo^2,3,4,*, Xiaotong He¹, Peiying Zhang¹

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.085456 - 13 August 2026

Abstract Multimodal Entity Linking (MEL) aims to map ambiguous mentions in multimodal contexts to their corresponding entities in a multimodal knowledge base. However, existing methods still face limitations in terms of feature extraction granularity, the depth of cross-modal interaction, and architectural coupling. To address these issues, we propose a Two-stage Decoupled Matching Network (TDMN) for multimodal entity linking. The matching process is divided into two stages: intra-modal matching and cross-modal interaction. In the intra-modal stage, textual and visual inputs are processed independently. The framework then proceeds to the cross-modal interaction stage, following the principle of “enhancement… More >

Bareera Anam, Muhammad Asim, Muhammad Nadeem Ali, Byung-Seo Kim^*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.084949 - 13 August 2026

Abstract The rapid evolution of communication networks, driven by the expansion of heterogeneous environments such as 6G, Internet of Things (IoT), and edge computing, has exposed a critical research gap in the lack of unified frameworks that jointly address intelligent network control and quantum-resilient security. Existing networking protocols were originally designed under static configurations and classical security assumptions, making them increasingly inadequate for dynamic, large-scale, and intelligent infrastructures exposed to quantum-enabled threats. At the same time, the emergence of Quantum Computing (QC) introduces severe security risks, as widely used cryptographic mechanisms supporting protocols such as Transport… More >

Zheng Yao¹, Jie Liu¹, Changjun Deng^2,3,*, Wang Lin^2,3

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.084892 - 13 August 2026

Abstract Mobile edge computing (MEC) is an effective paradigm for supporting latency-sensitive and computation-intensive intelligent applications. However, in dynamic mobile-edge network scenarios, mobile terminals experience time-varying wireless links due to mobility. Tasks may also arrive unpredictably, while multiple terminals compete for limited edge resources. As a result, MEC systems may suffer from service congestion and unbalanced resource utilization, which increases end-to-end latency and energy consumption. This paper investigates cooperative task offloading in dynamic MEC networks. The considered system comprises one macro base station and multiple small base stations equipped with edge-computing resources. In each time slot,… More >

Adeel Iqbal^1,#,*, Muhammad Faisal Siddiqui^2,#,*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.084851 - 13 August 2026

Abstract Hop-constrained packet routing is a fundamental problem in wireless sensor networks (WSNs), where latency constraints, energy limitations, and practical feasibility requirements greatly restrict routing choices. Traditional methods based on shortest path and greedy routing have low complexity but cannot adapt to dynamic network changes well, while reinforcement learning for routing has the potential to adapt to network variations but has not been well explored in the hard hop-constrained setting. The current study attempts to fill the gap by modeling hop-constrained routing as the decision-making problem in a finite-horizon setting. An integrated simulation environment is proposed… More >

Yunrui Bi^1,*, Qiliang Yang¹, Qinglin Ding¹, Bin Ran², Kun Liu¹, Mingjie Zhang¹

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.084267 - 13 August 2026

Abstract To improve regional traffic signal coordination under uncertain and dynamic traffic conditions, this paper proposes a hybrid Type-2 fuzzy reinforcement learning framework integrated with Beetle Antennae Search (BAS) and Deep Q-Network (DQN), named Type-2 fuzzy Beetle Antennae Search and Deep Q-Network (T2-BAS-DQN). In this framework, DQN remains active during online signal control, while the Type-2 fuzzy module provides uncertainty-aware correction for phase selection and green-time adjustment. BAS is used only in the offline training stage to optimize a low-dimensional parameter vector related to fuzzy correction, reward adjustment, and coordination pressure. A 3 × 3 Simulation… More >

Tahani Alsubait^*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.083550 - 13 August 2026

Abstract The recent sophistication of contemporary cyber threats, such as advanced persistent threats (APTs), zero-day exploits, and polymorphic malware, has revealed serious limitations of traditional rule-based and shallow machine learning detection systems. This paper introduces a new self-managed cyber threat detection and response model, CyberSentinel-LLM, that leverages a fine-tuned large language model (LLM) and a multi-agent reinforcement learning system. The framework employs a LoRA-adapted LLaMA-3-8B backbone (fine-tuned on domain-specific cybersecurity log data using Low-Rank Adaptation with rank r = 16) for contextual log analysis, semantic threat classification, and automated incident response through four specialised agents: Detection,… More >

Tallha Akram^1,*, Sadiq Ahmad^2,*, Meshal Alharbi³

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.081458 - 13 August 2026

Abstract Scalability limitations, privacy risks, and lack of adaptability remain key challenges in centralized medical digital win (MDT) architectures. While federated learning (FL) mitigates the need to share raw data, it often lacks adaptability to dynamic clinical environments and does not fully integrate formal privacy guarantees into the learning process. To address these challenges, this paper proposes a decentralized, federated, multi-agent reinforcement learning (F-MARL) framework to coordinate MDTs in the presence of partial observability. The framework is formulated as a multi-agent partially observable Markov decision process (MA-POMDP), enabling distributed policy optimization in heterogeneous and uncertain clinical… More >

Ximing Zhang^1,*, Zhuohuan Li², Xuexia Quan¹, Kai Cheng², Yang Yu²

Energy Engineering, Vol.123, No.9, 2026, DOI:10.32604/ee.2025.073912 - 06 August 2026

Abstract The “N-1” criterion represents a fundamental principle for assessing the reliability of power systems in static security analysis. Existing studies mainly rely on centralized single-agent reinforcement learning frameworks, where centralized control is difficult to cope with regional autonomy and communication delays. In high-dimensional state–action spaces, these approaches often suffer from low efficiency and unstable policies, limiting their applicability to large-scale grids. To address these issues, this paper proposes a Multi-Agent Deep Reinforcement Learning (MADRL) method enhanced with Curriculum Learning (CL) and Prioritized Experience Replay (PER). The proposed framework adopts a Centralized Training with Decentralized Execution… More >

Wei Wang¹, Hao Guo¹, Cheng Jian¹, Yi Yu¹, Quanmin Jiang¹, Chunyu Wang^2,*

FDMP-Fluid Dynamics & Materials Processing, Vol.22, No.7, 2026, DOI:10.32604/fdmp.2026.085147 - 31 July 2026

Abstract To overcome the inherent limitations of conventional post-cementing acidification, including limited acid penetration into the formation and the potential impairment of zonal isolation, a novel pre-cementing acidification approach is proposed. This method aims to remove near-wellbore formation damage before cementing operations. Its feasibility, however, critically depends on the physicochemical compatibility between residual acid and the subsequent cementing fluids, namely spacer fluids and cement slurries. In this study, a comprehensive series of laboratory experiments was conducted to evaluate the effects of residual acid on flushing efficiency, rheological compatibility, and thickening time. The results show that residual… More >