This paper presents Hy-LIFT (Hybrid LLM-Integrated Fault Diagnosis Toolkit), a multi-stage framework for interpretable and data-efficient fault diagnosis in 5G/6G networks that integrates a high-precision interpretable rule-based engine (IRBE) for known patterns, a semi-supervised classifier (SSC) that leverages scarce labels and abundant unlabeled logs via consistency regularization and pseudo-labeling, and an LLM Augmentation Engine (LAE) that generates operator-ready, context-aware explanations and zero-shot hypotheses for novel faults. Evaluations on a five-class, imbalanced Dataset-A and a simulated production setting with noise and label scarcity show that Hy-LIFT consistently attains higher macro-F1 than rule-only and standalone ML baselines while maintaining strong per-class precision/recall (≈0.85–0.93), including minority classes, indicating robust generalization under class imbalance. IRBE supplies auditable, high-confidence seeds; SSC expands coverage beyond explicit rules without sacrificing precision; and LAE improves operational interpretability and surfaces potential “unknown/novel” faults without altering classifier labels. The paper’s contributions are as follows: (i) a reproducible, interpretable baseline that doubles as a high-quality pseudo-label source; (ii) a principled semi-supervised learning objective tailored to network logs; (iii) an LLM-driven explanation layer with zero-shot capability; and (iv) an open, end-to-end toolkit with scripts to regenerate all figures and tables. Overall, Hy-LIFT narrows the gap between brittle rules and opaque black-box models by combining accuracy, data efficiency, and auditability, offering a practical path toward trustworthy AIOps in next-generation mobile networks.

Content Delivery Networks (CDNs) have evolved to meet surging data demands and stringent low-latency requirements driven by emerging applications like high-definition video streaming, virtual reality, and IoT. This paper proposes a hybrid CDN architecture that synergistically combines edge caching, Multi-access Edge Computing (MEC) offloading, and reinforcement learning (Q-learning) for adaptive routing. In the proposed system, popular content is cached at radio access network edges (e.g., base stations) and computation-intensive tasks are offloaded to MEC servers, while a Q-learning agent dynamically routes user requests to the optimal service node (cache, MEC server, or origin) based on the network state. The study presented detailed system design and provided comprehensive simulation-based evaluation. The results demonstrate that the proposed hybrid approach significantly improves cache hit ratios and reduces end-to-end latency compared to traditional CDNs and simpler edge architectures. The Q-learning-enabled routing adapts to changing load and content popularity, converging to efficient policies that outperform static baselines. The proposed hybrid model has been tested against variants lacking MEC, edge caching, or the RL-based controller to isolate each component’s contributions. The paper concludes with a discussion on practical considerations, limitations, and future directions for intelligent CDN networking at the edge.

Foundation models (FMs) large AI systems pre-trained on broad, heterogeneous data are increasingly embedded in scientific practice. Prior work has addressed this development in a piecemeal fashion: surveys of FM applications are confined to single domains, while reasoning taxonomies catalog general capabilities without mapping them to the full sequence of scientific work. We present FRAME-S (Framework for Reasoning with AI Models in Science), a four-dimensional framework characterising how foundation models reason scientifically. The four dimensions are Formal Reasoning (deductive and symbolic inference from premises to conclusions), Relational Reasoning (analogical transfer of structure across scientific domains), Abductive Reasoning (hypothesis generation from incomplete evidence), and Multi-modal Evidence Synthesis (integration of text, images, structured data and simulation output into coherent inferences). Each dimension is grounded in the philosophy of scientific method and mapped to the complete discovery lifecycle. We situate FRAME-S within a three-stage model of scientific paradigm evolution, propose reasoning transition thresholds specifying what a system must achieve to move between stages, derive five design principles with an operationalisation protocol for each dimension, and provide formal mathematical definitions specifying measurable properties. An empirical benchmark analysis applying the framework to published performance data for seven frontier models spanning 2023--2024 demonstrates that the four dimensions are empirically discriminable, that formal reasoning and multi-modal synthesis scale at markedly different rates, and that the Stage 1-to-2 formal reasoning threshold has been crossed by reasoning-specialised models.