Generative to Agentic AI: Survey, Conceptualization, and Challenges
cs.AI
Submitted: 2025-04-26
Updated: 2026-10-18
License: http://creativecommons.org/licenses/by/4.0/
The gist: Agentic AI builds upon Generative AI (GenAI).
Terminology
Abstract
Agentic AI builds upon Generative AI (GenAI). It constitutes the next major step in the evolution of AI with much stronger reasoning, learning, and interaction capabilities that enable more autonomous behavior to tackle complex, long-running tasks. Since the initial release of ChatGPT 3.5, Generative AI has seen widespread adoption, giving users firsthand experience. However, the distinction between Agentic AI and GenAI remains less well understood. To address this gap, our survey is structured in two parts. In the first part, we compare GenAI and Agentic AI using existing literature, discussing their key characteristics, how Agentic AI remedies limitations of GenAI, and the major steps in GenAI's evolution toward Agentic AI. We also distinguish between early Agentic AI aiming at reasoning and interacting and the increasingly emerging paradigm of self-improving Agentic AI that operates continuously and learns from its experiences by updating itself. This section is intended for a broad audience, including academics in both social sciences and engineering, as well as industry professionals. It provides the necessary insights to comprehend novel applications that are possible with Agentic AI but not with GenAI. In the second part, we deep dive into novel aspects of Agentic AI, including recent developments and practical concerns such as defining agents. Finally, we discuss several challenges that could serve as a future research agenda, while cautioning against risks that can emerge when exceeding human intelligence.
Sources
- Playing repeated games with Large Language Models
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
- Language Models are Few-Shot Learners
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
- Teaching Large Language Models to Self-Debug
- Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
- Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis
- Large Language Models as Tool Makers
- ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
- Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
- WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
- Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding
- ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
- Competitive Programming with Large Reasoning Models
- Stream of Search (SoS): Learning to Search in Language
- Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems