Retrieval Augmented Generation (RAG) has gradually emerged as a promising paradigm for enhancing the accuracy and factual consistency of content generated by large language models (LLMs). However, existing RAG studies primarily focus on retrieving isolated segments using similarity-based matching methods, while overlooking the intrinsic connections between them. This limitation hampers performance in RAG tasks. To address this, we propose QMKGF, a Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval Augmented Generation. First, we design prompt templates and employ general-purpose LLMs to extract entities and relations, thereby generating a knowledge graph (KG) efficiently. Based on the constructed KG, we introduce a multi-path subgraph construction strategy that incorporates one-hop relations, multi-hop relations, and importance-based relations, aiming to improve the semantic relevance between the retrieved documents and the user query. Subsequently, we designed a query-aware attention reward model that scores subgraph triples based on their semantic relevance to the query. Then, we select the highest score subgraph and enrich subgraph with additional triples from other subgraphs that are highly semantically relevant to the query. Finally, the entities, relations, and triples within the updated subgraph are utilised to expand the original query, thereby enhancing its semantic representation and improving the quality of LLMs’ generation. We evaluate QMKGF on the HotpotQA, MuSiQue, SQuAD, IIRC, and Culture datasets. On the HotpotQA dataset, our method achieves a ROUGE-1 score of 64.98%, surpassing the BGE-Rerank approach by 9.81 percentage points (from 55.17% to 64.98%). Experimental results demonstrate the effectiveness and superiority of the QMKGF approach. 

With the rapid growth of the Internet of Things, service explosion has become a serious challenge, hindering efficient collaboration in the Cyber-Physical-Social-Thinking (CPST) space. In response, the Internet of X (IoX) under the CPST framework is examined through an in-depth analysis from three dimensions: Internet of Things (IoT), Internet of People (IoP), and Internet of Thinking (IoTk). The rapid growth of IoT devices and data, the significant increase in the frequency of personalized interactions in IoP, and the explosive growth in the demand for IoTk cognitive services have caused existing communication, computing, and storage systems to face problems such as response delays and resource bottlenecks. To address the above challenges, a new AGI-based paradigm is proposed to address the problem of service explosion. The main mitigation approaches include interoperability, data/network efficiency, and security in IoT; scalable user management, personalization, and privacy in IoP; and brain-computer interaction, neural data processing, and brain information privacy in IoTk. Subsequently, the case of smart homes is employed to elaborate on how AGI alleviates the service explosion phenomenon in IoT, IoP, and IoTk scenarios. Finally, the development of artificial super intelligence is anticipated, and potential directions for future research are outlined. 

This paper explores the integration of Artificial Intelligence Generated Content (AIGC), a rapidly evolving branch of generative AI, with Human-Machine intelligence (HMI) to enhance the functionality of Intelligent Transportation Systems (ITS). As transportation systems grow increasingly complex, adaptive decision-making becomes essential for interpreting vast streams of real-time data from vehicles, infrastructure, and users. AIGC plays a transformative role in optimizing traffic flow through dynamic routing and real-time traffic management, while human intelligence ensures these systems remain responsive to evolving real-world conditions. For safety, AIGC is used to simulate complex driving scenarios for autonomous vehicle training and detect traffic anomalies, with human oversight providing contextual decisions in ambiguous situations. For sustainability, AIGC supports data-driven strategies to reduce emissions and energy use, while human expertise ensures alignment with ethical and environmental goals. This synergy enhances real-time decision-making, improving both accuracy and adaptability across ITS scenarios. The paper presents a comprehensive review of core and supporting AIGC technologies and their applications across key ITS domains. Case studies and initiatives from industry leaders demonstrate practical implementations of AIGC-driven HMI collaboration. To guide future deployments, we propose a conceptual five-layer evaluation framework for assessing AIGC-HMI systems, encompassing functional performance, human interaction, explainability, ethical compliance, and robustness. We also address challenges such as legacy system integration, data privacy, model bias, and scalability. The paper concludes by outlining future research directions, emphasizing the need for scalable, interpretable, and ethically aligned AIGC models. This work contributes to the development of intelligent, adaptive, and trustworthy transportation systems. 

The fidelity and utility of synthetic network traffic are critically compromised by architectural mismatch across heterogeneous network datasets and prevalent scalability failure. This study addresses this challenge by establishing an Architectural Selection Framework that empirically quantifies how data structure compatibility dictates the optimal fidelity-utility trade-off. We systematically evaluate twelve generative architectures (both non-AI and AI) across two distinct data structure types: categorical-heavy NSL-KDD and continuous-flow-heavy CIC-IDS2017. Fidelity is rigorously assessed through three structural metrics (Data Structure, Correlation, and Probability Distribution Difference) to confirm structural realism before evaluating downstream utility. Our results, confirmed over twenty independent runs (N = 20), demonstrate that GAN-based models (CTGAN, CopulaGAN) exhibit superior architectural robustness, consistently achieving the optimal balance of statistical fidelity and practical utility. Conversely, the framework exposes critical failure modes, i.e., statistical methods compromise structural fidelity for utility(Compromised fidelity), and modern iterative architectures, such as Diffusion Models, face prohibitive computational barriers, rendering them impractical for large-scale security deployment. This contribution provides security practitioners with an evidence-based guide for mitigating architectural failures, thereby setting a benchmark for reliable and scalable synthetic data deployment in adaptive security solutions.

This review explores the evolution from IoT to the Internet of Everything (IoX) within the cyber-physical-social-thinking (CPST) hyperspace, centering on the emerging challenge of ”relationship explosion.” As interconnected systems grow in scale and complexity, the exponential proliferation of internal (e.g., device coordination, data aggregation) and cross-space (e.g., streaming, translating, adapting) relationships leading to scalability, security, and real-time processing challenges. Through a systematic literature review guided by five research questions, we analyze how this relational explosion intensifies across IoX domains—spanning IoT, IoP, and IoTk—and undermines the efficacy of Artificial Narrow Intelligence (ANI) in managing dynamic, heterogeneous environments. This review proposes that Artificial General Intelligence (AGI) offers a transformative solution, enabling adaptive reasoning, cognitive firewalls, and unified decision-making to navigate complex relationship networks. AGI-driven methodologies enhance system resilience, security, and efficiency in aggregating, moderating, and evolving relationships across CPST spaces. The paper outlines a classification of relationship types, evaluates AGI’s advantages over ANI, and proposes a future research roadmap emphasizing ethical governance, human-AGI collaboration, and sustainable architectures. By framing IoX development around the management of relationship explosion, we provide a roadmap for future research, emphasizing interdisciplinary efforts, ethical governance, and sustainable frameworks to foster intelligent, socially aware IoX ecosystems. 

Cyberbullying has become a major challenge in the digital era, and many people, especially adolescents, use social media platforms to communicate and share information. Some exploit these platforms to embarrass others through messages, e-mails, speech, and public posts, causing severe psychological harm to victims. This study reviews existing research on technologies, approaches, datasets, and evaluation metrics for cyberbullying detection, while highlighting future directions and key challenges. The findings show that traditional models work reasonably well with small datasets but require constant updates; machine learning models face feature extraction and linguistic limitations; deep learning models perform better but lack multilingual and cross-lingual capabilities; and large language models (LLMs) achieve the highest performance, offering flexibility and rich linguistic features but face issues of high-energy use and real-time applicability. Addressing technological, methodological, dataset, and linguistic challenges will improve cyberbullying detection, helping to protect online communication and promote social responsibility. 

This article proposes the concept of Cyberism as a paradigm asserting that cyberspace necessitates its own integrated philosophical, scientific, and ethical framework. It aims at ensuring that technological advancement aligns with human values and sustainable progress.

The convergence of physical, social, and cognitive processes in cyberspace has created the Cyber-Physical-Social-Thinking (CPST) hyperspace, a multi-domain environment where entities and interactions span fundamentally distinct logical foundations. Existing space-specific logics, including causal logic in physical space, normative logic in social space, and cognitive logic in thinking space, were not designed for cross-space operation and exhibit critical structural limitations: representational misalignment, non-equivalent mapping, and reasoning inconsistency. Generative AI compounds these challenges by introducing endogenous cyberlogic, which can lead to opaque reasoning and semantic drift in safety-critical contexts. This paper presents Cyberlogic, a foundational framework for coordinating logic across the CPST hyperspace. Rather than replacing existing logics, Cyberlogic enables their principled coexistence through a four-layer Entity-Mapping-Reasoning-Governance architecture. It introduces the cyberentity as a unified carrier for cross-space representation, characterizes non-equivalent mappings, and distinguishes between cyberized logic (migrated from other spaces) and endogenous cyberlogic (originating within cyberspace). A formal symbolic system supports rigorous reasoning and extensibility. An information-theoretic perspective, based on mapping entropy and reasoning entropy, complements integrity evaluation by providing a quantitative measure of uncertainty propagation across spaces. Operational principles and the integrity evaluation perspective together guide deployment. The framework is illustrated through a smart city emergency response case study and further substantiated by a prototype implementation with information-theoretic analysis, demonstrating its practical coordination across all layers. Cyberlogic provides a theoretical foundation for organizing cross-space reasoning and governance in the transition from IoT to IoX, mitigating semantic drift, temporal misalignment, and logical inconsistency as generative AI assumes a greater role in cross-domain decision-making. 

With the growth of digital technologies and artificial intelligence, human existence is expanding into four interconnected spaces: physical (natural), social, thinking, and cyber. The interplay of these four spaces is reshaping the relationships between humans and nature, society, their inner selves, and the cyber world. The traditional tripartite philosophical system of Eastern culture (Daoism, Confucianism, and Buddhism) faces new challenges in explaining human existence and its relationship to these fundamental living spaces in the digital age. This paper proposes a new quadri-philosophical system, "Daoism, Confucianism, Buddhism, and Cyberism" based on the Cyber-Physical-Social-Thinking space. In this new system, Cyberism emerges as a new philosophical domain dedicated to exploring the relationship between humans and the cyber realm, including its existence and space, and responding to ongoing transformations in human life in the digital age. Specifically, this paper analyzes the new forms of existence and space, philosophical logic, and new applications and philosophical problems for each of the four philosophical dimensions, examining the contemporary relevance of Eastern philosophy in the context of digital society. This research seeks to contribute to ongoing discussions on Eastern philosophy and offers an interdisciplinary perspective for reflecting on the impact of emerging technologies on human existence.

The classification of major depressive disorders (MDDs) is a challenging task in clinical practice, especially in low-resource scenarios where generalization is essential for effective adaptation. Recent progress in meta-training large language models (LLMs) via in-context learning (ICL) offers promise for robust adaptation to unseen tasks without parameter updates. However, existing methods rely on multitask fine-tuning and do not fully exploit the optimization advantages of model-agnostic meta learning (MAML) techniques, limiting their generalization. This study proposes prompt-MAML, a novel method for meta-training LLMs that enhances multimodal ICL for classifying MDD tasks. The method integrates audio-textual features through a transformer-based cross-modal alignment module and incorporates bi-level optimization to learn generalizable model parameters that adapt well to unseen tasks. Extensive experiments demonstrate that prompt-MAML outperforms strong baseline models by an average improvement in macro-F1 of +4% on seen domains, +3% on unseen domains, and +3% in few-shot settings, demonstrating robustness and effectiveness in data-scarce and cross-domain clinical scenarios. Additionally, exploration depth is shown to play a key role in task performance, and further analysis of task complexity, modality, and optimiser configurations highlights critical design considerations for meta-training LLMs.