Knowledge Discovery and Extraction with Large Language Models, Retrieval-Augmented Generation, and Autonomous Agents: Methods, Architectures, and Applications

Dear Colleagues,

This Special Issue focuses on emerging methods and state-of-the-art approaches for knowledge discovery and extraction using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and autonomous AI agents. Recent advances in generative AI have significantly expanded the ability of intelligent systems to analyze large volumes of textual and multimodal data, enabling tasks such as information extraction, summarization, reasoning, and automated knowledge integration. However, effective knowledge discovery often requires reliable grounding in external information sources, structured reasoning, and interaction with complex data environments. Approaches such as RAG architectures and agentic AI frameworks address these challenges by combining generative models with retrieval mechanisms, knowledge bases, and tool-based reasoning capabilities. This Special Issue invites interdisciplinary contributions that explore innovative methods, architectures, and applications for AI-driven knowledge discovery, including work spanning natural language processing, multimodal learning, knowledge graphs, and intelligent agent systems.

This Special Issue invites original research articles, review papers, and application studies that address novel approaches to knowledge discovery and extraction. The scope includes, but is not limited to, the following topics:

Large Language Models for Knowledge Discovery

• Knowledge extraction and information discovery using LLMs;
• Named entity recognition, relation extraction, and event extraction with generative models;
• Fine-tuning and instruction tuning of LLMs for knowledge extraction tasks;
• Domain-adapted LLMs for scientific, medical, financial, or industrial knowledge discovery;
• Prompt engineering and in-context learning for knowledge discovery.

Retrieval-Augmented Generation

• Novel architectures and frameworks for RAG-based systems;
• Hybrid retrieval techniques combining vector, semantic, and symbolic search;
• Efficient indexing and retrieval strategies for large-scale knowledge bases;
• Evaluation and benchmarking of RAG systems;
• Methods for improving factual grounding and reducing hallucinations.

Autonomous Agents and Agentic AI

• LLM-based autonomous agents for knowledge discovery and reasoning;
• Multi-agent systems for collaborative knowledge extraction;
• Tool-augmented agents for information retrieval and analysis;
• Planning, reasoning, and decision-making in agent-based AI systems;
• Self-reflective and adaptive AI agents for knowledge exploration.

Natural Language Processing and Information Extraction

• Advanced NLP methods for structured knowledge extraction;
• Cross-document and long-context information extraction;
• Sentiment analysis, aspect-based analysis, and opinion mining;
• Semantic analysis and discourse-level knowledge discovery.

Multimodal Knowledge Discovery

• Knowledge extraction from multimodal data (text, images, audio, and video);
• Vision-language models and multimodal LLMs for knowledge discovery;
• Cross-modal retrieval and integration techniques;
• Multimodal reasoning and representation learning.

Knowledge Representation and Integration

• Knowledge graphs and semantic knowledge integration with LLMs;
• Graph-based reasoning and knowledge inference;
• Hybrid symbolic–neural approaches to knowledge discovery;
• Ontology learning and automated knowledge base construction.

Trustworthy and Explainable Knowledge Discovery

• Explainability and interpretability in AI-driven knowledge extraction;
• Reliability, bias mitigation, and fairness in generative models;
• Evaluation metrics and benchmarking frameworks for knowledge discovery systems;
• Privacy-preserving and responsible AI approaches.

Applications of AI-Driven Knowledge Discovery

• Scientific literature mining and automated research assistants;
• Healthcare and biomedical knowledge extraction;
• Social media analysis, trend detection, and misinformation monitoring;
• Enterprise knowledge management, decision support systems, and business intelligence;
• AI-powered customer service, chatbots, and virtual assistants;
• Smart cities, IoT data analytics, and industrial monitoring;
• E-commerce insights, recommendation systems, and market analysis;
• Legal and regulatory document analysis.

Dr. Shaheen Khatoon
Dr. Azhar Mahmood
Dr. Marek Sikora
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machine Learning and Knowledge Extraction is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• large language models
• knowledge discovery
• retrieval-augmented generation
• autonomous agents
• agentic AI
• natural language processing
• information extraction
• multimodal knowledge discovery
• knowledge representation
• knowledge integration
• trustworthy knowledge discovery
• explainable knowledge discovery
• AI-driven knowledge discovery applications