Also: This open textbook (or wiki channel) is intended to help librarians and other information professionals learn about AI. It is not, in itself, meant to be seen as promotion of AI. If anything, the goal is harms mitigation or harms reduction.
Introduction
"...AI agents (also referred to as compound AI systems or agentic AI) are a class of intelligent agents distinguished by their ability to operate autonomously in complex environments. Agentic AI tools prioritize decision-making over content creation and do not require human prompts or continuous oversight..." - Wikipedia
Agentic AI (see Wikipedia) refers to systems featuring agents who act autonomously, perceive their surrounding environment, make decisions, and take actions to achieve specific goals. Recently, studies of adaptation of previous AI applications were not exactly well done or rigorous enough, so researchers moved to agentic AI (Jiang et al, 2025).
AI agents are used to perform tasks during web browsing and potentially even perform browser actions on behalf of the user. An example of an advanced agentic AI system is Auto-GPT, an open-source tool that employs large language models (LLMs) to autonomously perform complex, multi-step tasks by breaking them into sub-goals, reasoning through each step, and utilizing external tools like web browsers, APIs, or file systems to achieve objectives. For instance, if tasked with "research and create a market analysis report," Auto-GPT can independently search the web, gather data, analyze it, and generate a structured report without needing constant human input. Its ability to plan, self-correct, and interact with external environments makes it a strong example of advanced agentic AI.
Another example of agentic AI (AAI) in action is Undermind.ai, developed by MIT researchers, a research assistant designed to streamline academic discovery by reading and analyzing hundreds of scientific papers, synthesizing findings, and delivering precise, relevant insights.
What is Agentic AI?
"...artificial intelligence systems can be broadly distinguished along a spectrum of autonomy, from narrow tools that perform single, well defined tasks to fully autonomous agents capable of independent goal pursuit across complex, multistep environments. Agentic AI occupies the advanced end of this spectrum. Unlike conventional AI systems that respond to isolated inputs and produce discrete outputs, agentic AI systems are designed to perceive their environment, formulate plans, execute sequences of actions, invoke external tools, and iteratively revise their behaviour in pursuit of a defined goal, often without requiring human intervention at each step." - Revesai et al, 2026
Examples of AAI in searching for and synthesizing information
AI-powered discovery and research assistants such as Elicit.com and Consensus are transforming how users engage with scholarly information. Rather than simply retrieving articles based on keywords, these tools interpret natural-language research questions, identify relevant literature, and generate concise summaries of key findings. They can also suggest next steps in the research process, such as refining a question, identifying gaps, or proposing related topics. In this sense, they function more like research agents than traditional search engines, actively guiding users through the discovery and sense-making process.
Scholarly agents such as Scite.ai and Connected Papers extend this capability by supporting deeper analysis of research papers. These tools map citation networks to reveal how studies are interconnected, evaluate the quality and context of evidence (for example, whether a paper is supported or disputed), and recommend relevant articles based on relationships in the literature. By revealing patterns and connections that would be difficult to identify manually, they help researchers navigate complex bodies of knowledge more efficiently and critically. However, there are traditional bibliographic databases and citation indexes such as the Web of Science and Scopus that do many of these things already.
Agentic AI represents a promising evolution of artificial intelligence in healthcare, with systems capable of operating autonomously to achieve defined clinical goals. However, the literature lacks conceptual clarity in distinguishing AI agents from Agentic AI, and few studies have rigorously explored their applications. We conducted a scoping review across five databases, identifying seven eligible studies spanning emergency medicine, oncology, radiology, and rehabilitation. The included systems demonstrated features such as autonomous operation, goal-directed behavior, action initiation, and, in some cases, multi-agent collaboration. Reported outcomes included high accuracy in cancer diagnosis, treatment planning, alert generation, coaching, and workflow optimization. Despite promising results, most studies were exploratory, limited in scope, and lacked robust clinical validation, with only one trial involving patients. These findings highlight both the potential and immaturity of Agentic AI in healthcare, underscoring the need for standardized definitions, regulatory guidance, and rigorous evaluation to ensure safe and effective integration into practice.
Agentic artificial intelligence (AAI) represents a significant evolution in the field of AI, moving beyond traditional and generative systems toward models characterized by autonomy, adaptivity, proactiveness, and decision agency. Unlike earlier AI paradigms that were reactive or limited to narrow tasks, AAI integrates reasoning, memory, planning, and tool orchestration to pursue complex objectives with minimal human oversight. Using a systematic literature review method, this study synthesizes current knowledge on AAI by examining its conceptual foundations, practical applications, and emerging research directions. Conceptually, AAI is distinguished from automation, generative AI, and multi-agent systems through its unique capacity to operate as a socio-technical partner in organizational and societal contexts. In practice, AAI is being applied across sectors such as healthcare, finance, manufacturing, education, and sustainability, enabling organizations to enhance decision support, optimize processes, and improve resilience in global business contexts. However, these advancements present significant challenges, including governance, transparency, accountability, workforce transformation, and integration with legacy systems. On the research front, four major streams dominate current scholarship: human–AI collaboration and co-agency; balancing AI autonomy with human control; governance and trust; and societal and ethical implications.
"...Cutting-edge agentic AI systems are built on foundation models that can be adapted to plan, reason, and interact with external tools to perform increasingly complex and specialized tasks. As these systems grow in capability and scope, adaptation becomes a central mechanism for improving performance, reliability, and generalization. In this paper, we unify the rapidly expanding research landscape into a systematic framework that spans both agent adaptations and tool adaptations. We further decompose these into tool-execution-signaled and agent-output-signaled forms of agent adaptation, as well as agent-agnostic and agent-supervised forms of tool adaptation. We demonstrate that this framework helps clarify the design space of adaptation strategies in agentic AI, makes their trade-offs explicit, and provides practical guidance for selecting or switching among strategies during system design... this paper aims to offer a conceptual foundation and practical roadmap for researchers and practitioners seeking to build more capable, efficient, and reliable agentic AI systems."
"...Recent large language models (LLMs) have demonstrated significant advancements, particularly in their ability to serve as agents, thereby surpassing their traditional role as chatbots. These agents can leverage their planning and tool utilization capabilities to address tasks specified at a high level. This suggests new potential to reduce the burden of administrative tasks and address current health care staff shortages. However, a standardized dataset to benchmark the agent capabilities of LLMs in medical applications is currently lacking, making it difficult to evaluate their performance on complex tasks in interactive health care environments..."
"...Agentic AI in medicine poses exciting opportunities but also new challenges that require careful investigation. We will need new frameworks for evaluating and regulating AI agents to ensure responsible use. Notably, in the USA, the Food and Drug Administration's review of medical AI devices treats each AI-enabled medical device as a tool for tackling a specific task. Thus, existing assessments typically focus on AI performance for a narrow medical output. New evaluation frameworks for AI agents could draw inspiration from more holistic assessments and extended real-world residencies that are integral to medical students’ training. Additionally, confabulation by AI agents is a risk and continuous performance monitoring will be essential. Multi-agent systems could play a part here with specialised safety or reliability agents assisting human supervisors in continuously evaluating the AI agent's behaviour..."
"evolution of Agentic AI, including Generative AI (GenAI) agents, has outpaced understanding of its applications, challenges, and strategic implications. This review explores Agentic AI focusing on its key attributes—autonomy, reactivity, proactivity, and learning ability; we identify a research gap in synthesizing the diverse capabilities of Agentic AI (e.g., multimodal processing, hierarchical architectures, and machine learning outsourcing) and actionable strategies for adoption. Findings reveal Agentic AI improves productivity, reduces costs, and drives innovation, though challenges such as privacy, security, and ethical concerns remain. Future research should focus on case studies to deepen understanding, explore impact (e.g., privacy, data security, labor market effects), and investigate integration."
"...AI Agents [are] modular systems driven by Large Language Models (LLMs) and Large Image Models (LIMs) for narrow, task-specific automation. Generative AI is positioned as a precursor, with AI Agents advancing through tool integration, prompt engineering, and reasoning enhancements. In contrast, Agentic AI systems represent a paradigmatic shift marked by multi-agent collaboration, dynamic task decomposition, persistent memory, and orchestrated autonomy."
"...Rapid advances in large language models (LLMs) have led to the emergence of agentic artificial intelligence (AI) systems capable of autonomously performing complex scientific tasks. This review examines recent developments in agentic AI, highlighting their transformative potential for ophthalmology research and clinical practice, and discusses associated ethical considerations."
Disclaimer
Note: Please use your critical reading skills while reading entries. No warranties, implied or actual, are granted for any health or medical search or AI information obtained while using these pages. Check with your librarian for more contextual, accurate information.
