mlsanityData to 14 Oct 2026

AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges

arXiv 2505.10468 ↗First posted 15 May 2025cs.AIcited by 169

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opportunities and challenges to clarify their divergent design philosophies and capabilities. We begin by outlining the search strategy and foundational definitions, characterizing AI Agents as modular systems driven and enabled by LLMs and LIMs for task-specific automation. Generative AI is positioned as a precursor providing the foundation, with AI agents advancing through tool integration, prompt engineering, and reasoning enhancements. We then characterize Agentic AI systems, which, in contrast to AI Agents, represent a paradigm shift marked by multi-agent collaboration, dynamic task decomposition, persistent memory, and coordinated autonomy. Through a chronological evaluation of architectural evolution, operational mechanisms, interaction styles, and autonomy levels, we present a comparative analysis across both AI agents and agentic AI paradigms. Application domains enabled by AI Agents such as customer support, scheduling, and data summarization are then contrasted with Agentic AI deployments in research automation, robotic coordination, and medical decision support. We further examine unique challenges in each paradigm including hallucination, brittleness, emergent behavior, and coordination failure, and propose targeted solutions such as ReAct loops, retrieval-augmented generation (RAG), automation coordination layers, and causal modeling. This work aims to provide a roadmap for developing robust, scalable, and explainable AI-driven systems.

Key facts. Cited by 169 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 122 of its 241 references that are in the map. First posted on arXiv 15 May 2025.

Builds on

122 of 241 references.

Closest ancestors · 20

Same direction, newest first

  1. 2025Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications26 Apr
  2. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems12 Apr
  3. 2025Agentic Large Language Models, a survey29 Mar
  4. 2025Agentic AI Needs a Systems Theory28 Feb
  5. 2025Human-Artificial Interaction in the Age of Agentic AI: A System-Theoretical Approach19 Feb
  6. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant3 Feb
  7. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  8. 2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAI27 Nov
  9. 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization3 Aug
  10. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation23 May
  11. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Review5 Apr
  12. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents20 Nov
8 more
  1. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  2. 2023Gentopia: A Collaborative Platform for Tool-Augmented LLMs8 Aug
  3. 2023AgentBench: Evaluating LLMs as Agents7 Aug
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  5. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun
  6. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar
  7. 2023Harms from Increasingly Agentic Algorithmic Systems20 Feb
  8. 2022A Generalist Agent12 May

Other references · 102

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  8. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  9. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  10. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  11. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  12. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
38 more
  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  3. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  4. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  6. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  7. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  8. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  9. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  10. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  11. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 344
  12. 2023The Impact of AI on Developer Productivity: Evidence from GitHub Copilotcited by 274
  13. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  14. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 255
  15. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  16. 2024AI Agents That Mattercited by 219
  17. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 198
  18. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  19. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 187
  20. 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
  21. 2023LLM in a flash: Efficient Large Language Model Inference with Limited Memorycited by 177
  22. 2025Multi-Agent Risks from Advanced AIcited by 163
  23. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 154
  24. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 150
  25. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Researchcited by 149
  26. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 136
  27. 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 134
  28. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 131
  29. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  30. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 97
  31. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 96
  32. 2023On Generative Agents in Recommendationcited by 90
  33. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
  34. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 83
  35. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 83
  36. 2024Robust agents learn causal world modelscited by 81
  37. 2024Visibility into AI Agentscited by 79
  38. 2024Beyond Browsing: API-Based Web Agentscited by 78

50 most cited of 102 All 102 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 76; 2026: 93.

169 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 59
  3. 2025From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflowscited by 58
  4. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 50
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  6. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 48
  7. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 45
  8. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 42
  9. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 29
  10. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agentscited by 29
  11. 2025AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunitiescited by 28
  12. 2025AgentBound: Securing Execution Boundaries of AI Agentscited by 23
38 more
  1. 2025What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commercecited by 22
  2. 2025Failure-Driven Workflow Refinementcited by 20
  3. 2025Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interactioncited by 19
  4. 2025AWorld: Orchestrating the Training Recipe for Agentic AIcited by 17
  5. 2025AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentationcited by 15
  6. 2025CoDA: Agentic Systems for Collaborative Data Visualizationcited by 15
  7. 2025Stop-RAG: Value-Based Retrieval Control for Iterative RAGcited by 14
  8. 2026Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agentscited by 14
  9. 2026From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaborationcited by 14
  10. 2025UAVs Meet Agentic AI: A Multidomain Survey of Autonomous Aerial Intelligence and Agentic UAVscited by 13
  11. 2026Beyond Similarity: Trustworthy Memory Search for Personal AI Agentscited by 12
  12. 2025Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigationcited by 11
  13. 2026Efficient LLM Serving for Agentic Workflows: A Data Systems Perspectivecited by 11
  14. 2025CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RLcited by 10
  15. 2026HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agentscited by 9
  16. 2025Position: Collaborative Agentic AI Needs Interoperability Across Ecosystemscited by 8
  17. 2025Agentic AI Home Energy Management System: A Large Language Model Framework for Residential Load Schedulingcited by 8
  18. 2026Agentic Business Process Management: A Research Manifestocited by 8
  19. 2025From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agentscited by 7
  20. 2025BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Webcited by 7
  21. 2025Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AIcited by 7
  22. 2025ACPs: Agent Collaboration Protocols for the Internet of Agentscited by 6
  23. 2025Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impactcited by 6
  24. 2025Detailed balance in large language model-driven agentscited by 6
  25. 2025Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threatscited by 6
  26. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  27. 2026Position: Human-Centric AI Requires a Minimum Viable Level of Human Understandingcited by 6
  28. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
  29. 2025AURA: A Multi-Modal Medical Agent for Understanding, Reasoning & Annotationcited by 5
  30. 2025Open Agent Specification (Agent Spec): A Unified Representation for AI Agentscited by 5
  31. 2025SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6Gcited by 5
  32. 2026Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignmentcited by 5
  33. 2026A Practical Guide to Agentic AI Transition in Organizationscited by 5
  34. 2026Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system securitycited by 5
  35. 2025OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Modelscited by 4
  36. 2025Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabularycited by 4
  37. 2025STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Callscited by 4
  38. 2026The Path Ahead for Agentic AI: Challenges and Opportunitiescited by 4

50 most cited of 169 All 169 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Distinguishing Autonomous AI Agents from Collaborative Agentic Systems: A Comprehensive Framework for Understanding Modern Intelligent Architectures
  2. 2025AI Agents: Evolution, Architecture, and Real-World Applications
  3. 2026Emergence of Agentic AI: A Review on Evolution, Background, Working Principles, Applications, Adoption Factors, and Future Research Directions
  4. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  5. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
  6. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
  7. 2025Agentic AI and Multiagentic: Are We Reinventing the Wheel?
  8. 2026From Prompt-Response to Goal-Directed Systems: The Evolution of Agentic AI Software Architecture