AI+ (AI Plus) is an interdisciplinary open access academic journal for artificial intelligence (AI) research, positioned at the intersection of AI technologies and their applications and/or applicability in multiple domains. The journal aims to bridge the gap between theoretical research and a diverse range of practical implementations, providing a platform for innovative applicable theory, methodologies, and case studies involving fielded applications of AI. Its scope encompasses the full range of topics within AI and its intersections with other scientific disciplines, offering a holistic view of the rapidly evolving landscape of intelligent systems.

Topics of interest include but are not limited to:

    Theoretical Work: Computational, mathematical, and analytical techniques such as machine learning, deep learning, reinforcement learning, learning theory, network dynamics, fuzzy logic, genetic algorithms, information theory, big data and knowledge engineering, knowledge representation and reasoning, and sensorimotor transformations.
    AI Applications: Natural language processing, computer vision, robotics, multi-agent systems, planning and scheduling, uncertainty modeling, intelligent systems, interdisciplinary applications involving AI, artificial life, cognitive science, computational learning theory, neurobiology, and pattern recognition, integration of AI with other scientific fields and the deployment of AI technologies across industries.

Special Issue on Advances in Retrieval-Augmented Generation in Large Language Models: Architectures, Applications, and Challenges
截稿日期: 2025-12-31

Large Language Models (LLMs) have made remarkable strides in natural language processing, yet they continue to face significant challenges, including issues related to information accuracy, timeliness, and opaque reasoning processes. One promising approach to address these issues is Retrieval-Augmented Generation (RAG). By integrating knowledge from external databases, RAG enhances the accuracy and reliability of generated content, particularly for knowledge-intensive tasks. This methodology enables continuous knowledge updates and the incorporation of domain-specific information, effectively combining the inherent knowledge of LLMs with the vast resources of external databases.

This Special Issue aims to provide a platform for sharing cutting-edge research, practical experiences, and innovative solutions related to the integration of RAG and LLMs. By gathering high-quality contributions, we seek to facilitate knowledge exchange and promote the adoption of LLMs and RAG across diverse fields.

We welcome contributions focused on the following topics:

    Innovative advancements and new architectures in RAG
    Real-world case studies and deployment experiences of RAG on LLMs
    Optimization techniques for enhanced performance and efficiency
    Applications of RAG in low-resource settings and languages
    Cross-disciplinary applications of LLMs
    Security and privacy concerns related to RAG applications
    Future trends and predictions in RAG development

We encourage researchers, practitioners, and experts from academia to participate and contribute to the advancement of the RAG and LLM fields. Submitted papers should reflect innovative research findings and practical insights, playing a crucial role in the evolution of this domain.