Agentic publications: redesigning scientific publishing in the age of thinking large language models

Purpose – This paper introduces the concept of “Agentic Publication (AP), ” a novel large language model (LLM)-driven framework designed to complement traditional scientific publishing by transforming papers into interactive knowledge systems that address challenges created by exponential growth in scientific literature. Design/methodology/approach – Our architecture integrates structured data (knowledge graphs and metadata) with unstructured content (text and multimedia) through retrieval-augmented generation and multi-agent verification. The system provides interfaces for humans and artificial agents, offering narrative explanations alongside machine-readable outputs. Implementation leverages vector databases for semantic search, knowledge graphs for structured reasoning and collaborative verification agents. Findings – Our proof-of-concept demonstration showcases multilingual interaction, Application Programming Interface (API) accessibility, continuous knowledge flow and structured knowledge representation. The framework enables dynamic updating of knowledge, synthesis of new findings and customizable detail levels. Practical implications – The system is a powerful companion for researchers navigating complex knowledge landscapes, offering tailored information access across disciplines while addressing ethical considerations through automated validation, expert oversight and transparent governance. Originality/value – The AP represents a transformative approach to scientific communication by creating responsive knowledge synthesis systems while maintaining scientific rigor. Integrating multi-agent verification with traditional publishing pathways creates a more efficient, accessible and collaborative research ecosystem, particularly valuable in interdisciplinary fields. Highlights – The Agentic Publication transforms static scientific papers into dynamic, interactive knowledge systems powered by LLMs The architecture combines structured and unstructured data with retrieval-augmented generation (RAG) and multi-agent verification processes The framework provides distinct interfaces for humans and artificial agents, enabling both narrative explanations and machine-readable outputs Ethical considerations are addressed through automated validation, expert oversight and transparent governance principles A proof-of-concept demonstrates a practical implementation while preserving compatibility with traditional scientific publishing workflows