Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
98 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

ProAgent: From Robotic Process Automation to Agentic Process Automation (2311.10751v2)

Published 2 Nov 2023 in cs.RO, cs.AI, and cs.CL

Abstract: From ancient water wheels to robotic process automation (RPA), automation technology has evolved throughout history to liberate human beings from arduous tasks. Yet, RPA struggles with tasks needing human-like intelligence, especially in elaborate design of workflow construction and dynamic decision-making in workflow execution. As LLMs have emerged human-like intelligence, this paper introduces Agentic Process Automation (APA), a groundbreaking automation paradigm using LLM-based agents for advanced automation by offloading the human labor to agents associated with construction and execution. We then instantiate ProAgent, an LLM-based agent designed to craft workflows from human instructions and make intricate decisions by coordinating specialized agents. Empirical experiments are conducted to detail its construction and execution procedure of workflow, showcasing the feasibility of APA, unveiling the possibility of a new paradigm of automation driven by agents. Our code is public at https://github.com/OpenBMB/ProAgent.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Towards intelligent robotic process automation for bpmers. arXiv preprint arXiv:2001.00804, 2020.
  2. Do as i can, not as i say: Grounding language in robotic affordances. ArXiv preprint, abs/2204.01691, 2022.
  3. Graph of thoughts: Solving elaborate problems with large language models. arXiv preprint arXiv:2308.09687, 2023.
  4. Large language models as tool makers. arXiv preprint arXiv:2305.17126, 2023.
  5. D3ba: a tool for optimizing business processes using non-deterministic planning. In Business Process Management Workshops: BPM 2020 International Workshops, Seville, Spain, September 13–18, 2020, Revised Selected Papers 18, pp.  181–193. Springer, 2020a.
  6. From robotic process automation to intelligent process automation: –emerging trends–. In Business Process Management: Blockchain and Robotic Process Automation Forum: BPM 2020 Blockchain and RPA Forum, Seville, Spain, September 13–18, 2020, Proceedings 18, pp.  215–228. Springer, 2020b.
  7. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848, 2023.
  8. Yiru Chen. Monte carlo tree search for generating interactive data analysis interfaces. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp.  2837–2839, 2020.
  9. Mary Cummings. Automation bias in intelligent time critical decision support systems. In AIAA 1st intelligent systems technical conference, pp.  6313, 2004.
  10. On the evaluation of intelligent process automation. arXiv preprint arXiv:2001.02639, 2020.
  11. Automation bias: a systematic review of frequency, effect mediators, and mitigators. Journal of the American Medical Informatics Association, 19(1):121–127, 2012.
  12. Automatic business process structure discovery using ordered neurons lstm: a preliminary study. arXiv preprint arXiv:2001.01243, 2020.
  13. Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992, 2023.
  14. Robotic process automation. Electronic markets, 30(1):99–106, 2020.
  15. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato (eds.), International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pp.  9118–9147. PMLR, 2022.
  16. Robotic process automation: systematic literature review. In Business Process Management: Blockchain and Central and Eastern Europe Forum: BPM 2019 Blockchain and CEE Forum, Vienna, Austria, September 1–6, 2019, Proceedings 17, pp.  280–295. Springer, 2019.
  17. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38, 2023.
  18. Robotic process and cognitive automation: the next phase. SB Publishing, 2018.
  19. Automated discovery of data transformations for robotic process automation. arXiv preprint arXiv:2001.01007, 2020.
  20. Interactive task and concept learning from natural language instructions and gui demonstrations. arXiv preprint arXiv:1909.00031, 2019.
  21. On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661, 2020.
  22. Multipurpose intelligent process automation via conversational assistant. arXiv preprint arXiv:2001.02284, 2020.
  23. n8n. n8n.io - a powerful workflow automation tool. URL https://n8n.io/.
  24. Webgpt: Browser-assisted question-answering with human feedback. ArXiv preprint, abs/2112.09332, 2021.
  25. OpenAI. OpenAI: Introducing ChatGPT, 2022. URL https://openai.com/blog/chatgpt.
  26. OpenAI. Gpt-4 technical report, 2023.
  27. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442, 2023.
  28. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334, 2023.
  29. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023a.
  30. Creator: Disentangling abstract and concrete reasonings of large language models through tool creation. arXiv preprint arXiv:2305.14318, 2023b.
  31. Webcpm: Interactive web search for chinese long-form question answering. arXiv preprint arXiv:2305.06849, 2023a.
  32. Tool learning with foundation models. arXiv preprint arXiv:2304.08354, 2023b.
  33. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789, 2023c.
  34. Business process automation. ARIS in practice, 2004.
  35. Toolformer: Language models can teach themselves to use tools. ArXiv preprint, abs/2302.04761, 2023.
  36. Algorithm of thoughts: Enhancing exploration of ideas in large language models. arXiv preprint arXiv:2308.10379, 2023.
  37. Reflexion: Language agents with verbal reinforcement learning, 2023.
  38. Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427, 2023.
  39. A review of business process mining: state-of-the-art and future trends. Business Process Management Journal, 14(1):5–22, 2008.
  40. Process mining: from theory to practice. Business Process Management Journal, 18(3):493–512, 2012.
  41. unipath. The uipath business automation platform. URL https://www.uipath.com/.
  42. Wil Van Der Aalst. Process mining: Overview and opportunities. ACM Transactions on Management Information Systems (TMIS), 3(2):1–17, 2012.
  43. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023a.
  44. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432, 2023b.
  45. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682, 2022.
  46. Robotic process automation–a systematic literature review and assessment framework. arXiv preprint arXiv:2012.11951, 2020.
  47. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023.
  48. Webshop: Towards scalable real-world web interaction with grounded language agents. Advances in Neural Information Processing Systems, 35:20744–20757, 2022a.
  49. React: Synergizing reasoning and acting in language models. ArXiv preprint, abs/2210.03629, 2022b.
  50. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601, 2023.
  51. Large language model as autonomous decision maker. arXiv preprint arXiv:2308.12519, 2023.
  52. Zapier. Zapier — automation makes you move forward. URL https://zapier.com/.
  53. Siren’s song in the ai ocean: A survey on hallucination in large language models. arXiv preprint arXiv:2309.01219, 2023.
Citations (15)
View on Semantic Scholar

Summary

  • The paper introduces APA as a novel automation paradigm that leverages LLMs for dynamic workflow construction and decision-making.
  • It employs an Agentic Workflow Description Language with JSON and Python to facilitate autonomous and interpretable process automation.
  • Experimental results on the n8n platform demonstrate ProAgent’s potential in transforming complex, human-instructed tasks into efficient automated workflows.

Overview of "ProAgent: From Robotic Process Automation to Agentic Process Automation"

The paper "ProAgent: From Robotic Process Automation to Agentic Process Automation" introduces Agentic Process Automation (APA) as a novel paradigm to address the limitations of traditional Robotic Process Automation (RPA). The focus is on integrating LLMs to facilitate more intelligent automation through dynamic decision-making and workflow construction.

Introduction

The evolution of automation technology, from simple mechanical devices to digital automation, has continually aimed to reduce human intervention in various processes. RPA, predominating in the digital era, excels in handling repetitive, rule-based tasks but falls short when complexity or human-like intelligence is required. With the emergence of LLMs, the paper proposes APA to overcome these limitations using LLM-based agents for enhanced automation.

Methodology

The paper highlights two primary advancements in APA:

  1. Agentic Workflow Construction: LLM-based agents autonomously construct workflows based on human instructions. The proposed "Agentic Workflow Description Language" employs JSON structure for data flow and Python code for control flow, leveraging LLMs' pre-trained understanding of programming concepts.
  2. Agentic Workflow Execution: This involves the use of DataAgent and ControlAgent to make dynamic decisions during workflow execution. DataAgent addresses complex data processing tasks, while ControlAgent takes over intricate decision-making processes, thus enhancing flexibility in workflow automation.

ProAgent Implementation

ProAgent exemplifies APA's framework by integrating the agent-driven workflow construction and execution within a unified architecture. Key aspects include:

  • Workflow Description Language: Utilizing JSON and Python, the language supports creating complex and dynamic workflows that LLMs can easily interpret and generate.
  • Dynamic Decision-Making with Agents: ProAgent incorporates DataAgent for data-intensive tasks and ControlAgent for decision-critical workflow branches.
  • Workflow Construction Process: The iterative process involves defining and implementing actions, orchestrating workflows, and validating through dynamic testing.

Experimentation and Results

Through proof-of-concept experiments on the n8n platform, ProAgent successfully demonstrates its capability to generate and execute workflows from human instructions. The empirical results underscore the feasibility of APA, demonstrating how ProAgent dynamically constructs workflows and integrates agents for complex task management.

Implications and Discussion

The introduction of APA and ProAgent has both theoretical and practical implications:

  • Relation to Tool Learning: ProAgent embodies an integration of tool utilization and creation, offering a novel approach by generating complex workflows as composite tools.
  • Process Mining Synergy: The integration of Process Mining can optimize workflow construction and provide insights into workflow efficiency, leading to continuous improvement.
  • Addressing Automation Bias: As automation technologies embed more intelligence, the risk of automation bias intensifies. The development of robust, interpretable, and safe APA frameworks is essential.

Conclusion

The paper contributes significantly to the evolving field of automation by leveraging LLMs for intelligent process automation. ProAgent is pioneering in its approach to offload intelligent tasks traditionally requiring human oversight, offering a glimpse into the future of automated industrial and corporate workflows. As technology advances, APA could redefine the landscape of automation, making it more efficient, adaptable, and intelligent.

Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - OpenBMB/ProAgent: An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation (692 stars)
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube