The Age of Autonomous Agents: A Bibliometric Review of Agentic AI Architectures, Applications, and Emerging Challenges Large Language Models, Agentic AI, Multi-Agent Systems, AI Agents, Generative AI, Retrieval-Augmented Generation, Bibliometric Analysis
Main article
Abstract
The rapid evolution of large language models (LLMs) has catalyzed a shift from passive AI systems toward autonomous agentic architectures capable of reasoning, memory, tool use, and multi-agent collaboration. This bibliometric review characterizes the emerging field through 810 publications retrieved from the Web of Science Core Collection for the period 2023–2025. Annual output rose sharply over this window—from 4 publications in 2023 to 96 in 2024 and 710 in 2025—accompanied by a parallel rise in citations, indicating rapid mainstream adoption. Author-keyword analysis reveals a landscape dominated by large language models, artificial intelligence, and multi-agent systems, with agentic AI, generative AI, and retrieval-augmented generation (RAG) emerging as core themes. Research output is geographically concentrated, led by China and the United States, and is distributed across a broad range of engineering, applied-science, and domain-specific journals rather than a single specialist venue, reflecting the field's cross-disciplinary uptake. Synthesizing this corpus, we organize the technical landscape around reasoning, memory, tool integration and RAG, and multi-agent orchestration; survey application domains spanning healthcare, scientific discovery, education, and software engineering, with emerging activity in finance and law; and analyze the principal challenges—hallucination, trust and robustness, inter-agent coordination, scalability, and governance. The review provides a structured, evidence-based map of agentic AI research to orient researchers and practitioners navigating this rapidly evolving field.
