Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension

Adem Ait, Javier Luis Cánovas Izquierdo, Jordi Cabot

Abstract

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. Current business process modeling languages fall short when it comes to specifying these new mixed collaborative scenarios. In this exploratory 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 metamodeling 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.

Introduction

As Large Language Models (LLMs) evolve into autonomous agents, they are increasingly integrated into multi-agent systems (MAS) to solve complex tasks. However, these agents must collaborate with humans in "mixed" environments. Current workflow modeling standards like BPMN fall short in this context, typically treating an AI agent as just another "Service Task" or a "User." This masks critical nuances of agentic behavior, such as non-determinism (confidence levels), reflection strategies (self-correction), and complex conflict resolution (voting or debate).

The Agentic BPMN Extension

To address these gaps, we utilized the built-in extension mechanism of BPMN 2.0 to add "agent-aware" features without breaking the existing standard. The extension focuses on three primary areas:

  1. Agent Profiling (AgenticLane): We extended the concept of a "Lane" to include a Profile (defining roles like 'manager' or 'worker') and Uncertainty (a trust score from 0-100). By treating trust as a first-class citizen, the workflow can programmatically branch; for instance, triggering human review if an agent's confidence falls below a specific threshold.
  2. Agent Reflection (AgenticTask): We introduced a specific task type assigned with a reflection mode—Self-reflection, Cross-reflection (feedback from other agents), or Human-reflection. This formalizes the "inner loop" of LLM improvement, reducing visual clutter in diagrams.
  3. Collaboration & Merging: We extended Gateways and Message Flows to define how agents cooperate. This includes specific logic for Voting-based, Role-based, Debate-based, and Competition-based collaboration.

Graphical Notation and Implementation

To ensure practical utility, we developed a graphical notation following principles of "semiotic clarity." We utilize a consistent "agent marker" (a small robot-head icon) with letter modifiers to denote specific behaviors (e.g., 'v' for voting). This allows the new agentic symbols to be easily distinguishable from standard human tasks while remaining familiar to BPMN users.

Proposed graphical notation for agentic BPMN elements.

The extension has been implemented as a functional modeling editor using the Sirius framework (an Eclipse project), allowing developers to drag and drop these new agentic elements into their process diagrams.

Case Study: Bug Resolution Workflow

The expressiveness of this extension is demonstrated through a bug-resolution process involving a human user, a human maintainer, and three distinct AI agents. As shown in the workflow below, the notation clearly distinguishes between human-initiated tasks (like submitting a report) and agentic cooperation (like reproducing and fixing bugs).

A complex bug-resolution workflow modeled using the proposed agentic BPMN extension.

Conclusion and Future Work

This paper presents an exploratory first step toward formalizing human-agentic workflows. While the current tool focuses on modeling, future work will involve building code generators to translate these diagrams into executable code for agent frameworks like LangGraph or CrewAI. Additionally, we plan to refine how uncertainty propagates through a process and conduct empirical user studies to validate the effectiveness of the proposed notation in real-world engineering scenarios.

Summary updated

Abstract

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 whose 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 exploratory 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 metamodeling 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.
BibTeX
@inproceedings{ait2025towards,
  author = {Adem Ait and Javier Luis Cánovas Izquierdo and Jordi Cabot},
  title = {{Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension}},
  booktitle = {SEAA},
  year = {2025},
  doi = {10.1007/978-3-032-04190-6\_22},
}
Figure