Agentic AI-Enabled Autonomous Business Process Management: Design and Evaluation of a Multi-Agent Workflow System (MAWS)
##plugins.themes.bootstrap3.article.main##
Abstract
Traditional Business Process Management (BPM) faces significant challenges in addressing the increasing complexity, uncertainty, and dynamic nature of modern business environments due to its reliance on static rule-based automation approaches. Although Artificial Intelligence (AI) has been increasingly integrated into BPM through Intelligent Process Automation, process mining, and predictive analytics, most existing solutions remain focused on task-level automation and have not achieved process-level autonomy. This limitation highlights the need for autonomous workflow architectures capable of adaptive decision-making and dynamic process orchestration. To address this gap, this study proposes a Multi-Agent Workflow System (MAWS) as an Agentic Artificial Intelligence-based framework for autonomous Business Process Management. The research adopts the Design Science Research (DSR) methodology, encompassing problem identification, artifact design and development, demonstration, and evaluation through five complementary validity dimensions: instrument validity, technical validity, design validity, purpose validity, and generalization. The evaluation results indicate that MAWS improves process execution efficiency, reduces human intervention requirements, and enhances processing accuracy compared with traditional Robotic Process Automation (RPA) approaches. Furthermore, the autonomous agents embedded within MAWS demonstrate capabilities for goal-oriented reasoning, multi-step planning, self-correction, and adaptive workflow orchestration under dynamic operational conditions. The primary contribution of this research lies in the development and validation of a BPM architecture based on multi-agent reasoning that bridges the gap between Agentic AI theory and enterprise-scale autonomous workflow implementation. The findings suggest that Agentic AI has the potential to transform BPM from rule-driven automation into goal-driven autonomous operations, while emphasizing the importance of robust AI governance mechanisms to ensure transparency, accountability, and operational trustworthiness.
##plugins.themes.bootstrap3.article.details##
[2] F. Imgrund and C. Janiesch, “Understanding the need for new perspectives on BPM in the digital age: an empirical analysis,” in International Conference on Business Process Management, 2019, pp. 288–300. doi: https://doi.org/10.1007/978-3-030-37453-2_24.
[3] A. Baiyere, H. Salmela, and T. Tapanainen, “Digital transformation and the new logics of business process management,” Eur. J. Inf. Syst., vol. 29, no. 3, pp. 238–259, 2020, doi: https://doi.org/10.1080/0960085X.2020.1718007.
[4] A. Surana, S. Kumara*, M. Greaves, and U. N. Raghavan, “Supply-chain networks: a complex adaptive systems perspective,” Int. J. Prod. Res., vol. 43, no. 20, pp. 4235–4265, 2005, doi: https://doi.org/10.1080/00207540500142274.
[5] M. Bédard, A. Leshob, I. Benzarti, H. Mili, R. Rab, and O. Hussain, “A rule‐based method to effectively adopt robotic process automation,” J. Softw. Evol. Process, vol. 36, no. 11, p. e2709, 2024, doi: https://doi.org/10.1002/smr.2709.
[6] A. Kernytska, “Beyond Optimization: The Evolving Role of Business Process Management in Industry Transformation,” Zesz. Nauk. Wyższej Szk. Bank. w Pozn., vol. 103, no. 4, pp. 111–122, 2023, doi: https://doi.org/10.58683/dnswsb.635.
[7] C. Paterson, R. Calinescu, S. Manandhar, and D. Wang, “Using unstructured data to improve the continuous planning of critical processes involving humans,” in 2019 IEEE/ACM 14th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS), 2019, pp. 25–31. doi: https://doi.org/10.1109/SEAMS.2019.00013.
[8] P. Badakhshan, K. Conboy, T. Grisold, and J. vom Brocke, “Agile business process management: A systematic literature review and an integrated framework,” Bus. Process Manag. J., vol. 26, no. 6, pp. 1505–1523, 2020, doi: https://doi.org/10.1108/BPMJ-12-2018-0347.
[9] D. Adrian, P. Diaconu, F. Margareta-Stela, and D. Camelia, “The Road to Autonomy: A Systematic Review Through AI in Autonomous Vehicles,” Electronics, vol. 14, no. 21, p. 4174, 2025, doi: 0.3390/electronics14214174.
[10] A. Oliveira, A. Silva, D. Camara, E. Silva, and L. Santiago, “Process Automation with BPM and Emerging Technologies for Service and Industrial Process Optimization: Systematic Mapping,” Simpósio Bras. Sist. Informação, vol. 22, no. 1, pp. 85–94, 2025, doi: https://doi.org/10.5753/sbsi.2025.246014.
[11] D. D. Otros and V. Otras, “Exploring the Impact of Artificial Intelligence on Enterprise Modeling,” Int. J. Enterp. Model., vol. 13, no. 2, pp. 53–61, 2019, doi: https://doi.org/10.35335/emod.v13i2.8.
[12] D. Calvanese et al., “Agentic business process management: A research manifesto,” Inf. Syst., vol. 140, no. 9, p. 102738, 2026, doi: https://doi.org/10.1016/j.is.2026.102738.
[13] M. T. Cuomo and P. Foroudi, Quantum Level Business Model: A New Managerial Perspective. Springer, 2025. doi: https://doi.org/10.1007/978-3-031-92052-3.
[14] D. Martino, C. Perlangeli, B. Grottoli, L. La Rosa, and M. Pacella, “A Knowledge-Driven Framework for AI-Augmented Business Process Management Systems: Bridging Explainability and Agile Knowledge Sharing,” AI, vol. 6, no. 6, p. 110, 2025, doi: https://doi.org/10.3390/ai6060110.
[15] P. Fettke and C. Di Francescomarino, “Business process management and artificial intelligence: Literature survey and future research,” KI-Künstliche Intelligenz, vol. 39, no. 2, pp. 67–79, 2025, doi: https://doi.org/10.1007/s13218-025-00891-y.
[16] C. H. V. de Moraes et al., “Robotic process automation and machine learning: a systematic review,” Brazilian Arch. Biol. Technol., vol. 65, no. 1–12, p. e22220096, 2022, doi: https://doi.org/10.1590/1678-4324-2022220096.
[17] L. Patrício, L. Varela, and Z. Silveira, “Integration of artificial intelligence and robotic process automation: Literature review and proposal for a sustainable model,” Appl. Sci., vol. 14, no. 21, p. 9648, 2024, doi: https://doi.org/10.3390/app14219648.
[18] S. Khantong and P. Sriboonlue, “Robotic Process Automation in Business Process Management: A Systematic Literature Review and an Integrated Framework,” Technologies, vol. 14, no. 4, p. 225, 2026, doi: https://doi.org/10.3390/technologies14040225.
[19] W. Jin, N. Wang, L. Zhang, X. Tian, B. Shi, and B. Zhao, “A Review of AI-Driven Automation Technologies: Latest Taxonomies, Existing Challenges, and Future Prospects.,” Comput. Mater. Contin., vol. 84, no. 3, 2025, doi: 10.32604/cmc.2025.067857.
[20] P. Jorzik, S. P. Klein, D. K. Kanbach, and S. Kraus, “AI-driven business model innovation: A systematic review and research agenda,” J. Bus. Res., vol. 182, p. 114764, 2024, doi: https://doi.org/10.1016/j.jbusres.2024.114764.
[21] L. S. Goecks, M. de Souza, T. P. Librelato, and L. R. Trento, “Design Science Research in practice: review of applications in Industrial Engineering,” Gestão & Produção, vol. 28, no. 1–19, p. e5811, 2021, doi: https://doi.org/10.1590/1806-9649-2021v28e5811.
[22] T. Haryanti, N. A. Rakhmawati, A. P. Subriadi, and A. Tjahyanto, “The Design Science Research Methodology (DSRM) for self-assessing digital transformation maturity index in Indonesia,” in 2022 IEEE 7th International Conference on Information Technology and Digital Applications (ICITDA), 2022, pp. 1–7. doi: https://doi.org/10.1109/ICITDA55840.2022.9971171.
[23] K. Peffers, T. Tuunanen, M. A. Rothenberger, and S. Chatterjee, “A design science research methodology for information systems research,” J. Manag. Inf. Syst., vol. 24, no. 3, pp. 45–77, 2007, doi: https://doi.org/10.2753/MIS0742-1222240302.
[24] S. Kroop, “Artifact validity in design science research (DSR): A comparative analysis of three influential frameworks,” in International Conference on Design Science Research in Information Systems and Technology, 2025, pp. 199–215. doi: https://doi.org/10.1007/978-3-031-93976-1_13.
[25] M. Muntean and F. D. Militaru, “Design science research framework for performance analysis using machine learning techniques,” Electronics, vol. 11, no. 16, p. 2504, 2022, doi: https://doi.org/10.3390/electronics11162504.
[26] Abhilash, “Harnessing AI for BPM: Streamlining complex workflows and enhancing efficiency,” J. Artif. Intell. Res., vol. 3, no. 1, pp. 385–431, 2024, doi: https://doi.org/10.36227/techrxiv.173532331.17776706/v1.
[27] Y. K. Dwivedi et al., “Agentic AI Systems: What It Is and Isn’t,” Glob. Bus. Organ. Excell., vol. 45, no. 3, pp. 253–263, 2026, doi: https://onlinelibrary.wiley.com/doi/abs/10.1002/joe.70018.
[28] M. Dumas, F. Milani, and D. Chapela-Campa, “Agentic business process management systems,” in International Conference on Business Process Management, 2025, pp. 3–14. doi: https://doi.org/10.1007/978-3-032-13426-4_1.
[29] J. García, “Moving From Process Optimization to Autonomous Operations: AI in BPM Trends for 2026 and Beyond,” Technology Evaluation Centers, 2026. https://www3.technologyevaluation.com/publications/ai-bpm-trends-2026-63822
[30] G. Mishra, “Autonomous AI Agents for Enterprise Workflow Orchestration in HR Platforms,” Int. J. Res. Appl. Innov., vol. 7, no. 6, pp. 11873–11887, 2024.
[31] S. Gerlach, “Principles of AI Business Integration: A Workflow-Driven Framework for Engineering the AI-Powered Enterprise,” Available SSRN 6160587, vol. 3, no. 3, pp. 1–32, 2026, doi: https://dx.doi.org/10.2139/ssrn.6160587.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.