COMPAS: COllaborative process Mining with robotic Process automation and generative AI for the design and Sustainability of hyper-connected processes

• Andrea Delgado Universidad de la República
• Daniel Calegari Universidad ORT Uruguay
• Martín Rubio Universidad de la República
• Félix García University of Castilla-La Mancha
• Renato Jorcín Universidad de la República
• Leonel Peña Universidad de la República
• Daniela Andrade Universidad de la República
• Laura González Universidad de la República
• Hajo Reijers Utrecht University
• Jana-Rebecca Rehse University of Mannheim
• Lorenzo Rossi University of Camerino

Resumo

Process Mining (PM) provides techniques for analyzing event logs to support evidence-based improvement and process discovery. However, multi-organizational collaborative processes remain difficult to design and analyze due to their distributed nature and technological diversity. Recent advances in Large Language Models and Robotic Process Automation offer new opportunities to support process discovery, modeling, and automation. In parallel, Green BPM emphasizes the need to incorporate sustainability considerations into process design and execution. This project aims to define and evaluate techniques, algorithms, methodologies, and strategies for integrating PM with RPA and Generative AI, considering sustainability elements for the design, automation, and analysis of hyper-connected collaborative processes for e-Government, leveraging real data from the Uruguayan Digital Government Agency (AGESIC), linking theoretical and practical results.

Referências

Berti, A., Kourani, H., Häfke, H., Li, C.-Y., and Schuster, D. (2024). Evaluating large language models in process mining: Capabilities, benchmarks, and evaluation strategies. In Enterprise, Business Process and Inf. Systems Modeling, pages 13–21. Springer.

Dumas, M., Milani, F., and Chapela-Campa, D. (2026). Agentic business process management systems. CoRR, abs/2601.18833.

Dumas, M., Rosa, M. L., Leno, V., Polyvyanyy, A., and Maggi, F. M. (2022). Robotic Process Mining, pages 468–491. Springer.

Dumas, M., Rosa, M. L., Mendling, J., and Reijers, H. A. (2018). Fundamentals of Business Process Management, 2nd Ed. Springer.

Giaccio, R., Gerolami, E., Calegari, D., and Delgado, A. (2026). Structured evaluation of robotic process automation (rpa) tools. In BPM Workshops. Springer-In press.

Grohs, M., Abb, L., Elsayed, N., and Rehse, J.-R. (2024). Large language models can accomplish business process management tasks. In BPM Workshops. Springer.

Hernández González, A., Calero, C., Pérez Parra, D., and Mancebo, J. (2019). Approaching green BPM characterisation. Journal of Software: Evol. and Process, 31(2).

Jongeling, H. E., Lu, X., Beerepoot, I., van de Weerd, I., and Reijers, H. A. (2023). Getting your rpa priorities straight with process mining: The plost framework. In ECIS 2023 Research Papers.

Kitchenham, B. (2004). Procedures for performing systematic reviews. Technical Report TR/SE-0401, Joint Report, Keele, UK.

Kitchenham, B. A. and Charters, S. (2007). Guidelines for performing systematic literature reviews in soft. eng. Technical Report EBSE 2007-001, Joint Rep., Keele, UK.

Rubio, M., Delgado, A., and García, F. (2026). Enabling sustainability-aware process mining: A systematic approach for measurement and registration of sustainability data. In ICPM Workshops. Springer-In press.

van der Aalst, W., Bichler, M., and Heinzl, A. (2018). Robotic process automation. Bussiness and Information Systems Engineering, 60:269–272.

van der Aalst, W. M. P. (2016). Process Mining - Data Science in Action, 2nd ed. Springer.

Wohlin, C., Runeson, P., Höst, M., Ohlsson, M. C., Regnell, B., and Wesslén, A. (2024). Experimentation in Software Engineering. Springer.

Yin, R. K. (2017). Case Study Research and Applications: Design and Methods, 6th ed. SAGE Publications, Inc.