A Review of AI-Driven Automation Technologies: Latest Taxonomies, Existing Challenges, and Future Prospects

1. Executive Office of the President. Artificial Intelligence, Automation, and the Economy. Washington, DC, USA: The White House; 2016 [Internet]. [cited 2023 Dec 24]. Available from: https://obamawhitehouse.archives.gov/blog/2016/12/20/artificial-intelligence-automation-and-economy.

2. Bhattacharyya · Confluence of artificial intelligence and robotic process automation · 202310.1007/978-981-19-8296-5 ↗

3. The impact of artificial intelligence on employment: the role of virtual agglomeration10.1057/s41599-024-02647-9 ↗

4. Liu G, Zhao P, Liu L, Guo Y, Xiao H, Lin W, et al. LLM-powered GUI agents in phone automation: surveying progress and prospects. arXiv:2504.19838. 2025.10.20944/preprints202501.0413.v1 ↗

5. Ke Z, Jiao F, Ming Y, Nguyen XP, Xu A, Long DX, et al. A survey of frontiers in LLM reasoning: inference scaling, learning to reason, and agentic systems. arXiv:2504.09037. 2025.

6. A survey on large language model based autonomous agents10.1007/s11704-024-40231-1 ↗

7. Automatically correcting large language models: surveying the landscape of diverse automated correction strategies10.1162/tacl_a_00660 ↗

8. WebArena: a realistic web environment for building autonomous agents

9. AutoAgents: a framework for automatic agent generation

10. Pandya K, Holia M. Automating customer service using LangChain: building custom open-source GPT Chatbot for organizations. arXiv:2310.05421. 2023.

11. Zhang X, Chen H, He Y, Niu W, Li Q. Automatically generating rules of malicious software packages via large language model. arXiv:2504.17198. 2025.10.1109/DSN64029.2025.00072 ↗

12. Tang · Findings of the Association for Computational Linguistics: ACL 2024 · 2024 · 599

13. Enhancing diagnostic capability with multi-agents conversational large language models10.1038/s41746-025-01550-0 ↗

14. Guarda · Advanced research in technologies, information, innovation and sustainability · 2025 · 97

15. Applying robotic process automation (RPA) in auditing: a framework10.1016/j.accinf.2019.100433 ↗

16. Li Y, Yu Y, Li H, Chen Z, Khashanah K. TradingGPT: multi-agent system with layered memory and distinct characters for enhanced financial trading performance. arXiv:2309.03736. 2023.

17. Business optimization of financial centers in pharmaceutical enterprises based on robotic process automation technology10.1109/ACCESS.2025.3550962 ↗

18. Kim Y, Iturrate I, Sloth C, Kim H. Safety-ensured control framework for robotic endoscopic task automation. arXiv:2503.08214. 2025.

19. Yao T, Ban M, Lu B, Pei Z, Qi P. Sim4EndoR: a reinforcement learning centered simulation platform for task automation of endovascular robotics. arXiv:2504.05330. 2025.10.1109/ICRA55743.2025.11127627 ↗

20. Ruan J, Chen Y, Zhang B, Xu Z, Bao T, du Q, et al. TPTU: task planning and tool usage of large language model-based AI agents. In: NeurIPS 2023 Foundation Models for Decision Making Workshop; 2023 [Internet]. [cited 2025 Jul 9].

21. Liu Z, Yao W, Zhang J, Yang L, Liu Z, Tan J, et al. AgentLite: a lightweight library for building and advancing task-oriented LLM agent system. arXiv:2402.15538. 2024.

22. On grounded planning for embodied tasks with language models

23. TaskMatrix.AI: completing tasks by connecting foundation models with millions of APIs10.34133/icomputing.0063 ↗

24. Why are there still so many jobs? the history and future of workplace automation10.1257/jep.29.3.3 ↗

25. Leveraging software automation to transform the manufacturing industry10.60087/jklst.vol2.n1.p92 ↗

26. Robotic process automation and intelligent automation security challenges: a review

27. Hyperautomation-beyond RPA: leveraging automation to transform the manufacturing industries

28. Airtable. Airtable: the modern platform for building AI-powered apps; 2025 [Internet]. [cited 2024 Nov 12]. Available from: https://www.airtable.com/.

29. Figma I. Figma: The collaborative interface design tool. Figma, Inc.; 2025 [Internet]. [cited 2025 Feb 24]. Available from: https://www.figma.com/.

30. Zapier. Zapier: the most connected AI orchestration platform; 2024 [Internet]. [cited 2024 Oct 24]. Available from: https://zapier.com/.

31. Team RA, Contributors. AgentGPT: autonomous AI agent platform. GitHub; 2023 [Internet]. [cited 2025 Feb 9]. Available from: https://github.com/reworkd/AgentGPT.

32. EconAgent: large language model-empowered agents for simulating macroeconomic activities

33. Abdellaif OH, Nader A, Hamdi A. LMRPA: large language model-driven efficient robotic process automation for OCR. arXiv:2412.18063. 2024.10.1007/978-3-031-91351-8_4 ↗

34. Integrating AI with robotic process automation (RPA): advancing intelligent automation systems

35. Robotic process automation in small enterprises: an investigation into application potential10.7250/csimq.2023-34.04 ↗

36. Botonic. Botonic: no-code chatbots; 2025 [Internet]. [cited 2025 Mar 19]. Available from: https://botonic.io/.

37. Voiceflow. Voiceflow: the fastest way to build advanced AI Agents; 2025 [Internet]. [cited 2025 Sep 17]. Available from: https://www.voiceflow.com/.

38. Quickbase. Quickbase: spend more time on work that matters; 2024. Quickbase helps you see, connect, and control your projects from day one to done-without the complexity [Internet]. [cited 2025 Jul 9]. Available from: https://www.quickbase.com/.

39. Yuan S, Song K, Chen J, Tan X, Li D, Yang D. EvoAgent: towards automatic multi-agent generation via evolutionary algorithms. In: Workshop on Open-World Agents: Synergizing Reasoning and Decision-Making in Open-World Environments (OWA-2024); 2024 [Internet]. [cited 2025 Jul 9]. Available from: https://openreview.net/forum?id=DdxAp2j3AP.

40. Intelligent space power automation

41. Google. Looker studio: no-code charts; 2025 [Internet]. [cited 2025 Apr 8]. Available from: https://lookerstudio.google.com/overview.

42. Webnode. Webnode: no-code website builder, Make your own website for free!. Webnode; 2024 [Internet]. [cited 2025 Mar 12]. Available from: https://www.webnode.com.

43. Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. OpenAI; 2019 [Internet]. [cited 2025 Jul 9]. Available from: https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf.

44. Contributors G. GPT Researcher: LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations. GitHub; 2024 [Internet]. [cited 2024 Aug 29]. Available from: https://github.com/assafelovic/gpt-researcher.

45. OpenAI, Jaech A, Kalai A, Lerer A, Richardson A, El-Kishky A, et al. OpenAI o1 system card. arXiv:2412.16720. 2024.

46. Retrieval-augmented generation for knowledge-intensive NLP tasks

47. Qian C, Liu W, Liu H, Chen N, Dang Y, Li J, et al. ChatDev: communicative agents for software development. arXiv:2307.07924. 2024.10.18653/v1/2024.acl-long.810 ↗

48. Chen D, Wang H, Huo Y, Li Y, Zhang H. GameGPT: multi-agent collaborative framework for game development. arXiv:2310.08067. 2023.

49. Wang S, Liu C, Zheng Z, Qi S, Chen S, Yang Q, et al. Avalon’s game of thoughts: battle against deception through recursive contemplation. arXiv:2310.01320. 2023.

50. Xu Y, Wang S, Li P, Luo F, Wang X, Liu W, et al. Exploring large language models for communication games: an empirical study on werewolf. arXiv:2309.04658. 2024.

51. Intrusive plug management system using chatbots in office environments

52. Dincy R. Arikkat, Abhinav M, Binu N, Parvathi M, Biju N, Arunima KS, et al. IntellBot: retrieval augmented LLM chatbot for cyber threat knowledge delivery. arXiv:2411.05442. 2024.10.1109/CICN63059.2024.10847404 ↗

53. Livathinos N, Auer C, Lysak M, Nassar A, Dolfi M, Vagenas P, et al. Docling: an efficient open-source toolkit for AI-driven document conversion. arXiv:2501.17887. 2025.

54. Prototyping and implementing Robotic Process Automation in accounting firms: benefits, challenges and opportunities to audit automation10.1016/j.accinf.2023.100641 ↗

55. Jain A, Paliwal S, Sharma M, Vig L, Shroff G. SmartFlow: robotic process automation using LLMs. arXiv:2405.12842. 2024.

56. Liu Z, Yao W, Zhang J, Xue L, Heinecke S, Murthy R, et al. BOLAA: benchmarking and orchestrating LLM-augmented autonomous agents. arXiv:2308.05960. 2023.

57. Bhatt A, Vaghela N. Med-Bot: an AI-powered assistant to provide accurate and reliable medical information. arXiv:2411.09648. 2024.10.36227/techrxiv.172651811.10262073/v1 ↗

58. Nam Y, Seo T, Shin G, Lee S, Im J. NOVI: chatbot system for university novice with BERT and LLMs. arXiv:2409.06192. 2024.

59. Qin Y, Liang S, Ye Y, Zhu K, Yan L, Lu Y, et al. ToolLLM: facilitating large language models to master 16000+ real-world APIs. arXiv:2307.16789. 2023.

60. Hong S, Zhuge M, Chen J, Zheng X, Cheng Y, Wang J, et al. MetaGPT: meta programing for a mmulti-agent collaborative framework. In: The Twelfth International Conference on Learning Representations; 2024 [Internet]; Vienna, Austria. [cited 2025 Jul 9]. Available from: https://openreview.net/forum?id=VtmBAGCN7o.

61. ReTA: recursively thinking ahead to improve the strategic reasoning of large language models

62. ALYMPICS: LLM agents meet game theory

63. CoMM: collaborative multi-agent, multi-reasoning-path prompting for complex problem solving

64. Explainable AI (XAI): a systematic meta-survey of current challenges and future opportunities10.1016/j.knosys.2023.110273 ↗

65. Chen W, Su Y, Zuo J, Yang C, Yuan C, Chan CM, et al. AgentVerse: facilitating multi-agent collaboration and exploring emergent behaviors. In: The Twelfth International Conference on Learning Representations; 2024 [Internet]; Vienna, Austria. [cited 2025 Jul 9]. Available from: https://openreview.net/forum?id=EHg5GDnyq1.

66. Robotic process automation-a systematic mapping study and classification framework10.1080/17517575.2021.1986862 ↗

67. Samek · Lecture notes in computer science · 2022 · 11700

68. TPTU-v2: boosting task planning and tool usage of large language model-based agents in real-world industry systems

69. Understanding user acceptance of robotic process automation: the user resistance perspective10.1108/IMDS-07-2024-0628 ↗

70. How to conduct successful business process automation projects? An analysis of key factors in the context of robotic process automation10.1108/BPMJ-06-2023-0465 ↗

71. Ferrag MA, Tihanyi N, Debbah M. From LLM reasoning to autonomous AI agents: a comprehensive review. arXiv:2504.19678. 2025.

72. Keskar NS, McCann B, Varshney LR, Xiong C, Socher R. CTRL: a conditional transformer language model for controllable generation. arXiv:1909.05858. 2019.

73. Li T, Yang YT, Pan Y, Zhu Q. From texts to shields: convergence of large language models and cybersecurity. arXiv:2505.00841. 2025.

74. Unleashing the emergent cognitive synergy in large language models: a task-solving agent through multi-persona self-collaboration

75. AI-enhanced robotic process automation: a review of intelligent automation innovations10.1109/ACCESS.2024.3513279 ↗

76. Hong Kong academic librarians’ attitudes toward robotic process automation10.1108/LHT-03-2022-0141 ↗

77. Feng X, Dou L, Li E, Wang Q, Wang H, Guo Y, et al. A survey on large language model-based social agents in game-theoretic scenarios. arXiv:2412.03920. 2024.

78. Yao S, Zhao J, Yu D, Du N, Shafran I, Narasimhan K, et al. ReAct: synergizing reasoning and acting in language models. arXiv:2210.03629. 2023.

79. Yang Z, Li L, Wang J, Lin K, Azarnasab E, Ahmed F, et al. MM-REACT: prompting ChatGPT for multimodal reasoning and action. arXiv:2303.11381. 2023.

80. API as method for improving robotic process automation

81. Automation of polymer pressing by robotic handling with in-process parameter optimization10.1016/j.robot.2024.104868 ↗

82. Blockchain and machine learning for intelligent automation in robotic process automation10.1007/s42979-025-03852-2 ↗

83. Shinn N, Cassano F, Berman E, Gopinath A, Narasimhan K, Yao S. Reflexion: language agents with verbal reinforcement learning. arXiv:2303.11366. 2023.

84. Foundational Autoraters: taming large language models for better automatic evaluation

85. Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications10.1109/TCYB.2020.2977374 ↗

86. Masterman T, Besen S, Sawtell M, Chao A. The landscape of emerging AI agent architectures for reasoning, planning, and tool calling: a survey. arXiv:2404.11584. 2024.

87. Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, et al. Language models are few-shot learners. arXiv:2005.14165. 2020.

88. Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, et al. LLaMA: open and efficient foundation language models. arXiv:2302.13971. 2023.

89. Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, et al. Llama 2: open foundation and fine-tuned chat models. arXiv:2307.09288. 2023.

90. Zhou P, Pujara J, Ren X, Chen X, Cheng HT, Le QV, et al. Self-Discover: large language models self-compose reasoning structures. arXiv:2402.03620. 2024.

91. Wu Q, Bansal G, Zhang J, Wu Y, Li B, Zhu E, et al. AutoGen: enabling next-gen LLM applications via multi-agent conversation. arXiv:2308.08155. 2023.

92. Zhou X, Zhu H, Mathur L, Zhang R, Yu H, Qi Z, et al. SOTOPIA: interactive evaluation for social intelligence in language agents. arXiv:2310.11667. 2024.

93. AgentCF: collaborative learning with autonomous language agents for recommender systems

94. Xie T, Zhou F, Cheng Z, Shi P, Weng L, Liu Y, et al. OpenAgents: an open platform for language agents in the wild. In: First Conference on Language Modeling; 2024 [Internet]; Philadelphia, PA, USA. [cited 2025 Jul 9]. Available from: https://openreview.net/forum?id=sKATR2O1Y0.

95. Weng L. LLM-powered autonomous agents. Lilian weng’s blog; 2023 [Internet]. [cited 2025 Feb 9]. Available from: https://lilianweng.github.io/posts/2023-06-23-agent/.

96. Tree of thoughts: deliberate problem solving with large language models

97. Xin H, Guo D, Shao Z, Ren ZZ, Zhu Q, Liu B, et al. Advancing theorem proving in LLMs through large-scale synthetic data. In: The 4th Workshop on Mathematical Reasoning and AI at NeurIPS’24; 2024 [Internet]. [cited 2025 Feb 9]. Available from: https://openreview.net/forum?id=TPtXLihkny.

98. SelfAPR: self-supervised program repair with test execution diagnostics

99. Zhang J, Xiang J, Yu Z, Teng F, Chen XH, Chen J, et al. AFlow: automating agentic workflow generation. In: The Thirteenth International Conference on Learning Representations; 2025 [Internet]; Singapore EXPO. [cited 2025 Feb 9]. Available from: https://openreview.net/forum?id=z5uVAKwmjf.

100. SciAgent: tool-augmented language models for scientific reasoning