Collaborative Workflow; LLM Agent; BPMN Extension; Autonomous Intelligent Agents; BPMN extension; Collaborative workflow; Complex task; Different domains; Language model; Large language model agent; Model agents; Performance; Work-flows; Theoretical Computer Science; Computer Science (all)
Abstract :
[en] Large Language Models (LLMs) have facilitated the definition of autonomous intelligent agents. Such agents have already demonstrated their potential in solving complex tasks in different domains. And they can further increase their performance when collaborating with other agents in a multi-agent system. However, the orchestration and coordination of these agents is still challenging, especially when they need to interact with humans as part of human-agentic collaborative workflows. These kinds of workflows need to be precisely specified so that it is clear who is responsible for each task, what strategies agents can follow to complete individual tasks or how decisions will be taken when different alternatives are proposed, among others. Current business process modeling languages fall short when it comes to specifying these new mixed collaborative scenarios. In this paper, we extend a well-known process modeling language (i.e., BPMN) to enable the definition of this new type of workflow. Our extension covers both the formalization of the new modeling concepts required and the proposal of a BPMN-like graphical notation to facilitate the definition of these workflows. Our extension has been implemented and is available as an open-source human-agentic workflow modeling editor on GitHub.
Disciplines :
Computer science
Author, co-author :
AIT-MIMOUNE FONOLLA, Adem ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PI Cabot
Izquierdo, Javier Luis Cánovas ; IN3 - UOC, Barcelona, Spain
CABOT, Jordi ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PI Cabot ; Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg
External co-authors :
yes
Language :
English
Title :
Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension
Publication date :
2025
Event name :
51st Euromicro Conference Series on Software Engineering and Advanced Applications (SEAA)
UNIVERSITA DEGLI STUDI DI SALERNO, DIPARTIMENTO DI INFORMATICA
Funding text :
This work is part of the project TED2021-130331B-I00 funded by MCIN/AEI/10.13039/501100011033 and European Union NextGenera-tionEU/PRTR; and BESSER, funded by the Luxembourg National Research Fund (FNR) PEARL program, grant agreement 16544475.
Brambilla, M., Cabot, J., Izquierdo, J.L.C., Mauri, A.: Better call the crowd: using crowdsourcing to shape the notation of domain-specific languages. In: International Conference on Software Language Engineering, pp. 129–138 (2017)
Ceballos, H.G., Flores-Solorio, V., Garcia, J.P.: A probabilistic BPMN normal form to model and advise human activities. In: Baldoni, M., Baresi, L., Dastani, M. (eds.) EMAS 2015. LNCS (LNAI), vol. 9318, pp. 51–69. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-26184-3 4
Dumas, M., Rosa, M.L., Mendling, J., Reijers, H.A.: Fundamentals of Business Process Management. Springer (2013)
Engeström, Y., Miettinen, R., Punamäki-Gitai, R.L.: Perspectives on activity theory. Cambridge University Press (1999)
Guo, T., et al.: Large language model based multi-agents: A survey of progress and challenges. In: International Joint Conference on Artificial Intelligence, pp. 8048–8057 (2024)
Herbert, L., Sharp, R.: Precise quantitative analysis of probabilistic business process model and notation workflows. J. Comput. Inf. Sci. Eng. 13(1) (2013)
Küster, T., Lützenberger, M., Heßler, A., Hirsch, B.: Integrating process modelling into multi-agent system engineering. Multiagent Grid Syst. 8(1), 105–124 (2012)
Liu, Y., et al.: Agent design pattern catalogue: a collection of architectural patterns for foundation model based agents. J. Syst. Softw. 220, 112278 (2025)
Moody, D.: The “physics” of notations: toward a scientific basis for constructing visual notations in software engineering. IEEE Trans. Software Eng. 35(6), 756–779 (2009)
OMG: Business process model and notation (bpmn) 2.0.2 specification (Jan 2014). https://www.omg.org/spec/BPMN, Accessed July 2024
Richardson, N., Kolovos, D., Garcia-Dominguez, A.: Aconite: towards generating sirius-based graphical editors from annotated metamodels. In: International Conference on Software Language Engineering, pp. 16–28 (2024)
Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. In: Conference on Neural Information Processing Systems (2023)
Stroppi, L.J.R., Chiotti, O., Villarreal, P.D.: Extending BPMN 2.0: method and tool support. In: Dijkman, R., Hofstetter, J., Koehler, J. (eds.) BPMN 2011. LNBIP, vol. 95, pp. 59–73. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25160-3 5
Wei, J., et al.: Emergent abilities of large language models. Trans. Mach. Learn. Res. 2022 (2022)
Wu, Q., et al.: Autogen: Enabling next-gen LLM applications via multi-agent conversation framework. CoRR abs/arXiv: 2308.08155 (2023)
Xi, Z., et al.: The rise and potential of large language model based agents: a survey. Sci. China Inf. Sci. 68(2), 121101 (2025)
