Aug 2026· Cognitive Computation· Vol 18· 0 citations· 134 references
TL;DR
A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.
Abstract
Large Language Model (LLM)–based agents are rapidly evolving from passive assistants into autonomous, tool-using, and collaborative systems capable of executing complex, long-horizon tasks across web, software, and physical environments. However, the current literature remains fragmented, with inconsistent terminology, ad hoc architectures, and limited evaluation standards, making it difficult to compare systems or deploy them reliably in real-world settings. This paper presents a unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance. We systematically analyze representative single-agent, tool-augmented, and multi-agent frameworks within this taxonomy, highlighting design trade-offs, capability scaling patterns, and recurring failure modes. Beyond architectural analysis, we review emerging evaluation methodologies that move beyond static benchmarks to assess agent behavior, robustness, grounding, and operational cost in interactive environments. Importantly, the survey emphasizes practical considerations for enterprise and safety-critical deployment, including access control, human-in-the-loop oversight, and policy enforcement. By unifying conceptual foundations with empirical trends and deployment constraints, this work provides a structured roadmap for researchers and practitioners to design, evaluate, and govern next-generation LLM-based agentic systems.
Large Language Models (LLMs) have spurred the development of agentic artificial intelligence systems that can reason autonomously, plan, use tools, integrate memory, and carry out multi-step tasks. Unlike conventional prompt-response systems, LLM-based agents extend generative models to goal-oriented architectures that can decompose complex objectives, interact with external environments, and coordinate actions in iterative workflows. The survey systematically reviews LLM-based agent frameworks, multi-agent collaboration architectures, internal communication mechanisms, emerging cross-system interoperability protocols, and open research challenges. The review uses a PRISMA-based methodology, including literature from 2020 to March 2026, with particular focus on prominent frameworks such as LangChain, AutoGPT, AutoGen, MetaGPT, CAMEL, ChatDev, and CrewAI. The survey discusses the transition from modular chain-oriented to stateful graph-oriented and autonomous execution models and presents a systematic taxonomy of multi-agent collaboration architectures, including hierarchical, peer-to-peer, and role-based models. It also reviews the main internal communication mechanisms used to facilitate coordination and information sharing between LLM-based agents and distinguishes them from emerging interoperability protocols designed to support interaction across heterogeneous agents, tools, services, and frameworks. The analysis indicates that the promise of LLM-based agents for scalable automation, collaborative reasoning, and complex workflow execution comes with significant challenges in long-horizon reliability, evaluation standardization, communication security, cost-efficient orchestration, governance, and the interpretability of emergent multi-agent behavior. The survey covers architectural evolution, collaboration patterns, communication mechanisms, framework-level characteristics, and open research challenges. This provides a structured foundation for future research on reliable and trustworthy agentic artificial intelligence systems.
Unknown authors· Journal of Smart Algorithms...· 0 citations
This paper synthesizes 27 benchmark, taxonomy, and audit papers (2023-2026), spanning 19 distinct benchmarks, into a cross-cutting taxonomy of agent limitations, the first synthesis that integrates evidence across tool use, planning, long-horizon reasoning, multi-agent coordination, safety, and measurement validity into a single, unified taxonomy of LLM agent limitations.
Wael S. Albayaydh, Rui Zhao, Ivan Flechais· 1 citation
Through applied case studies in pharmaceutical discovery and financial systems, common design patterns that make agentic systems successful are analyzed, and practical mitigation strategies for failure modes are discussed, such as verification pipelines, fallback mechanisms, and human-in-the-loop supervision.
Grace Hui Yang, P. Venkit, Hooman Sedghamiz et al.· Proceedings of the 32nd ACM...· 0 citations
This workshop aims to bring together researchers and practitioners to examine how enterprise AI agents can successfully move from prototypes to production, and focuses on three pillars: 1) Agent architectures and systems; 2) Enterprise applications and deployments; 3) Evaluation and governance.
Min Du, Anbang Xu, Jasmine Jaksic et al.· Proceedings of the 32nd ACM...· 0 citations
Agentic Artificial Intelligence (Agentic AI) represents a major advancement in the evolution of intelligent systems by enabling autonomous planning, decision-making, and action execution. Unlike traditional AI models, which are primarily reactive and designed to respond to predefined inputs, Agentic AI systems possess capabilities such as memory, reasoning, goal-oriented planning, tool integration, and dynamic adaptation to changing environments. These characteristics allow them to perform complex, multi-step tasks with minimal human intervention, making them suitable for applications across healthcare, finance, cybersecurity, robotics, education, and enterprise automation. This paper explores the conceptual foundations, architectural principles, and practical applications of Agentic AI while examining the key differences between conventional AI and autonomous agent-based systems. It presents a taxonomy that distinguishes reactive and agentic models, discusses single-agent and multi-agent orchestration frameworks, and analyzes the role of memory, planning, perception, and external tool usage in intelligent decision-making. The study also highlights the ethical, security, governance, and accountability challenges associated with deploying autonomous AI, including issues related to transparency, privacy, bias, reliability, and human oversight. As AI systems become increasingly capable of operating independently within complex environments, establishing robust governance and regulatory frameworks is essential. This paper proposes a comprehensive framework for the design, evaluation, and responsible deployment of Agentic AI, emphasizing safety, explainability, human-in-the-loop supervision, and ethical compliance. By integrating technical innovation with effective governance strategies, the proposed approach aims to maximize the benefits of Agentic AI while minimizing potential risks. The findings contribute to the growing body of research on trustworthy autonomous systems and provide practical guidance for developing secure, reliable, and human-centered Agentic AI solutions.
Dr. Nitin S. Shrirao, Mr. Dnyaneshwar S. Jadhav, Mithun B. Patil· Recent Trends in Mathematics· 0 citations
Agentic Artificial Intelligence (AI) represents a paradigm shift from static, task-specific systems to autonomous, goal-directed agents capable of reasoning, planning, learning, and acting with minimal human oversight. This paper synthesizes perspectives from philosophy, cognitive science, and AI to define agency, outline its key properties, and situate it in relation to existing paradigms such as reinforcement learning, symbolic reasoning, Belief–Desire–Intention (BDI) architectures, and embodied cognition. We present a taxonomy of agentic systems along dimensions of autonomy, cognitive capability, modality, and environmental interaction, highlighting current capabilities and limitations, and we critically delimit where such a taxonomy is informative and where a functional, closed-loop analysis of agent behavior must take over. The enabling technologies, including large language models, memory architectures, planning frameworks, tool-use mechanisms, and multimodal embodiment, are reviewed alongside diverse application domains ranging from autonomous research and creative systems to web automation and human–AI collaboration. We analyze safety, alignment, evaluation challenges, and emergent risks, dedicate a section to trustworthiness, privacy, and sustainability by bridging from trustworthy machine learning, verified autonomy, and privacy-preserving learning, and compile a comparative review of prominent benchmarks for assessing agentic behavior. Finally, we outline future research directions, including compositional and modular architectures, cooperative AI, simulation-based safe exploration, data-efficient and developmentally inspired learning, hybrid symbolic–neural systems, and strategies for robust alignment. By providing a comprehensive framework and critical analysis, this work aims to guide the development of agentic AI systems that are not only capable but also safe, trustworthy, and aligned with human values.