Generative AI, Large Language Models, and Agentic AI

Dear Colleagues,

Recent advances in Generative AI, foundation models, large language models (LLMs), multimodal learning, and reasoning systems are profoundly transforming the design and deployment of data-intensive applications. These technologies are enabling new ways to generate content, extract knowledge, support decision making, and interact with complex data ecosystems. Beyond traditional predictive AI, the field is now moving from generative and reasoning-capable models toward Agentic AI, namely intelligent systems able not only to produce outputs, but also to perceive context, plan multi-step actions, interact with tools and heterogeneous data sources, collaborate with humans and other agents, and continuously adapt their behavior in dynamic environments.

This evolution is particularly relevant to Big Data and Cognitive Computing, where the volume, velocity, variety, and distributed nature of data require more scalable, context-aware, and autonomous computational approaches. In such settings, modern intelligent systems rely not only on powerful models but also on structured data, metadata, memory, knowledge representations, and orchestration mechanisms that enable reliable, explainable, and effective operation at scale.

This Special Issue aims to collect high-quality contributions on the theories, methods, infrastructures, and applications of Generative AI, Large Language Models, and Agentic AI in data-driven environments. The topic is strongly aligned with the scope of Big Data and Cognitive Computing, as these paradigms increasingly depend on large-scale data management, knowledge extraction, retrieval, reasoning, tool use, workflow orchestration, and human-centered decision support. We welcome studies that advance both methodological foundations and real-world deployments, including cloud–edge and edge–cloud infrastructures, domain-specific intelligent assistants, multimodal generative systems, multi-agent collaboration, trustworthy and explainable AI, and autonomous decision-making pipelines.

In this Special Issue, original research articles and review papers are welcome. Research areas may include, but are not limited to, the following:

• Generative AI models and methods for big data and cognitive computing;
• Large language models for data understanding, summarization, reasoning, and decision support;
• Multimodal foundation models for text, vision, speech, and sensor-rich environments;
• LLM-based agents, autonomous workflows, and tool-augmented reasoning;
• Agentic AI architectures for big data analytics and cognitive computing;
• Multi-agent systems for collaborative analysis and decision support;
• Retrieval-augmented generation, memory, and knowledge-grounded intelligent systems;
• Data structures, metadata, and knowledge representations for generative and agentic systems;
• Agentic AI on cloud–edge and edge–cloud continuums;
• Autonomous data engineering, orchestration, and MLOps pipelines;
• Explainable, trustworthy, fair, safe, and accountable intelligent systems;
• Human-in-the-loop and human–agent collaboration models;
• Applications of generative and agentic AI in social media analysis, recommendation, healthcare, industry, finance, and smart cities;
• Benchmarking, evaluation methodologies, reproducibility, efficiency, and sustainability for generative and agentic AI.

We look forward to receiving your contributions.

Dr. Fabrizio Marozzo
Dr. Loris Belcastro
Dr. Şule Öztürk
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. Big Data and Cognitive Computing 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.