Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents

N. R. Jennings, “On agent-based software engineering,” Artificial Intelligence

2000

Earlier work this paper cites.

L. Busoniu, R. Babuska, & B. De Schutter, “A comprehensive survey of multiagent reinforcement learning,” IEEE Transactions on Systems, Man, and Cybernetics

2008

Earlier work this paper cites.

Z. Yang et al. , “HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering,” EMNLP

2018

Earlier work this paper cites.

M. Shridhar et al. , “ALFWorld: Aligning Text and Embodied Environments for Interactive Learning,” International Conference on Learning Representations (ICLR)

2020

Earlier work this paper cites.

D. Hendrycks et al. , “Measuring Massive Multitask Language Understanding,” International Conference on Learning Representations (ICLR)

2021

Earlier work this paper cites.

K. Cobbe et al. , “Training Verifiers to Solve Math Word Problems,” arXiv preprint arXiv:2110.14168

Original

2021

Earlier work this paper cites.

J. Wei et al. , “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” Advances in Neural Information Processing Systems (NeurIPS)

2022

Earlier work this paper cites.

M. Ahn et al. , “Do As I Can, Not As I Say: Grounding Language in Robotic Affordances,” Conference on Robot Learning (CoRL)

2022

Earlier work this paper cites.

A. Parisi, Y. Zhao, & N. Fiedel, “TALM: Tool Augmented Language Models,” arXiv preprint arXiv:2205.12255

Original

2022

Earlier work this paper cites.

S. Yao et al. , “ReAct: Synergizing Reasoning and Acting in Language Models,” arXiv preprint arXiv:2210.03629

Original

2023

Earlier work this paper cites.

G. Mialon et al. , “Augmented Language Models: a Survey,” Transactions on Machine Learning Research

2023

Earlier work this paper cites.

S. Hao et al. , “Reasoning with Language Model is Planning with World Model,” arXiv preprint arXiv:2305.14992

Original

2023

Earlier work this paper cites.

G. Mialon et al. , “GAIA: a benchmark for general AI assistants,” arXiv preprint arXiv:2311.12983

Original

2023

Earlier work this paper cites.

N. Shinn et al. , “Reflexion: Language Agents with Verbal Reinforcement Learning,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

T. Schick et al. , “Toolformer: Language Models Can Teach Themselves to Use Tools,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

S. G. Patil, T. Zhang, X. Wang, & J. E. Gonzalez, “Gorilla: Large Language Model Connected with Massive APIs,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

J. S. Park et al. , “Generative Agents: Interactive Simulacra of Human Behavior,” Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST)

2023

Earlier work this paper cites.

A. Madaan et al. , “Self-Refine: Iterative Refinement with Self-Feedback,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

A. Zhao et al. , “Expel: LLM Agents are Experiential Learners,” arXiv preprint arXiv:2308.10144

Original

2023

Earlier work this paper cites.

G. Li et al. , “CAMEL: Communicative Agents for ’Mind’ Exploration,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

C. Xu et al. , “MemGPT: Towards LLMs as operating systems,” arXiv preprint arXiv:2310.08560

Original

2023

Earlier work this paper cites.

X. Deng et al. , “Mind2Web: Towards a Generalist Agent for the Web,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

S. Zhou et al. , “WebArena: A Realistic Web Environment for Autonomous Agents,” Advances in Neural Information Processing Systems (NeurIPS)

2023

Earlier work this paper cites.

J. Liang et al. , “Code as Policies: Language Model Programs for Embodied Control,” International Conference on Robotics and Automation (ICRA)

2023

Earlier work this paper cites.

Y. Liu et al. , “Formalizing and Benchmarking Prompt Injection Attacks and Defenses,” arXiv preprint arXiv:2310.12815

Original

2023

Earlier work this paper cites.

Z. Jiang et al. , “Active Retrieval-Augmented Generation for Knowledge-Intensive NLP,” arXiv preprint arXiv:2305.06983

Original

2023

Earlier work this paper cites.

P. Manakul, A. Liusie, & M. J. F. Gales, “SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection,” Conference on Empirical Methods in Natural Language Processing (EMNLP)

2023

Earlier work this paper cites.

B. Xu et al. , “ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models,” arXiv preprint arXiv:2305.18323

Original

2023

Earlier work this paper cites.

L. Chen et al. , “Introspective Tips: Large Language Models with Self-Reflection,” arXiv preprint arXiv:2305.11598

Original

2023

Earlier work this paper cites.

J. Zhang et al. , “OMNI: Open-endedness via Models of human Notions of Interestingness,” arXiv preprint arXiv:2306.01711

Original

2023

Earlier work this paper cites.

X. Wang et al. , “Executable Code Actions Elicit Better LLM Agents,” International Conference on Machine Learning (ICML)

2024

Earlier work this paper cites.

J. Yang et al. , “SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering,” arXiv preprint arXiv:2405.15793

Original

2024

Earlier work this paper cites.

Y. Li et al. , “Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security,” arXiv preprint arXiv:2401.05459

Original

2024

Earlier work this paper cites.

S. Hong et al. , “MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework,” International Conference on Learning Representations (ICLR)

2024

Earlier work this paper cites.

Y. Yang et al. , “Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents,” arXiv preprint arXiv:2411.09523

Original

2024

Earlier work this paper cites.

L. Wang et al. , “A Survey on Large Language Model based Autonomous Agents,” Frontiers of Computer Science

2024

Earlier work this paper cites.

A. Li et al. , “Agent-oriented planning in multi-agent systems,” arXiv preprint arXiv:2410.02189

Original

2024

Earlier work this paper cites.

A. Kumar, “Building Autonomous AI Agents based AI Infrastructure,” International Journal of Computer Trends and Technology

2024

Earlier work this paper cites.

Y. Cheng et al. , “Exploring Large Language Model based Intelligent Agents,” arXiv preprint arXiv:2403.00000

Original

2024

Earlier work this paper cites.

S. Yao et al. , “Tree of Thoughts: Deliberate Problem Solving with Large Language Models,” Advances in Neural Information Processing Systems (NeurIPS)

2024

Earlier work this paper cites.

OpenAI, “Learning to reason with LLMs,” 2024. [Online]. Available: https://openai.com/index/learning-to-reason-with-llms/

2024

Earlier work this paper cites.

OpenAI, “o1 system card,” 2024. [Online]. Available: https://openai.com/index/openai-o1-system-card/

2024

Earlier work this paper cites.

C. Snell, J. Lee, K. Xu, & A. Kumar, “Scaling LLM test time compute optimally can be more effective than scaling model parameters,” arXiv preprint arXiv:2408.03314

Original

2024

Earlier work this paper cites.

LangChain AI, “LangGraph: building language agents as graphs,” 2024. [Online]. Available: https://github.com/langchain-ai/langgraph

2024

Earlier work this paper cites.

OpenAI, “Swarm,” 2024. [Online]. Available: https://github.com/openai/swarm

2024

Earlier work this paper cites.

Anthropic, “Introducing the Model Context Protocol,” 2024. [Online]. Available: https://www.anthropic.com/news/model-context-protocol

2024

Earlier work this paper cites.

Anthropic, “Model Context Protocol specification,” 2024. [Online]. Available: https://modelcontextprotocol.io/specification

2024

Earlier work this paper cites.

Anthropic, “Developing a computer use model,” 2024. [Online]. Available: https://www.anthropic.com/news/developing-computer-use

2024

Earlier work this paper cites.

OpenAI, “Introducing SWE bench Verified,” 2024. [Online]. Available: https://openai.com/index/introducing-swe-bench-verified/

2024

Earlier work this paper cites.

SWE bench, “SWE bench leaderboards,” 2024. [Online]. Available: https://www.swebench.com/

2024

Earlier work this paper cites.

Epoch AI, “FrontierMath: a benchmark for evaluating advanced mathematical reasoning in AI,” arXiv preprint arXiv:2411.04872

Original

2024

Earlier work this paper cites.

J. Wu et al. , “ τ \tau -bench: a benchmark for tool agent user interaction in real world domains,” arXiv preprint arXiv:2406.12045

Original

2024

Earlier work this paper cites.

R. Aksitov et al. , “REST Meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent,” arXiv preprint arXiv:2312.10003

Original

2024

Earlier work this paper cites.

H. Furuta et al. , “Language Model Agents Suffer from Compositional Decision Making,” arXiv preprint arXiv:2410.15037

Original

2024

Cited alongside, same era.

H. Qu & T. Xie, “Teaching Language Model Agents How to Self-Improve,” arXiv preprint arXiv:2410.12468

Original

2024

Cited alongside, same era.

Z. Liu et al. , “Proactive Conversational Agents with Inner Thoughts and Empathy,” arXiv preprint arXiv:2405.19464

Original

2024

Cited alongside, same era.

W. Zhong et al. , “MemoryBank: Enhancing Large Language Models with Long-Term Memory,” arXiv preprint arXiv:2305.10250

Original

2024

Cited alongside, same era.

C. Hu et al. , “ChatDB: Augmenting LLMs with Databases as their Symbolic Memory,” arXiv preprint arXiv:2306.03901

S. Hong et al. , “Enhancing Memory Retrieval in Generative Agents through LLM-Trained Cross Attention Networks,” arXiv preprint arXiv:2410.15693

Original

2025

Later among the works it cites.

Z. Xi et al. , “The Rise and Potential of Large Language Model Based Agents: A Survey,” Science China Information Sciences

2025

Later among the works it cites.

Y. Xia et al. , “AgentRM: Enhancing agent generalization with reward modeling,” arXiv preprint arXiv:2502.18407

Original

2025

Later among the works it cites.

Z. Xi et al. , “AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress,” arXiv preprint arXiv:2511.08325

Original

2025

Later among the works it cites.

AI CERTs Team, “RE-Bench: Economic Efficiency Factors in Agent Evaluation,” AI CERTs Technical Report