Agentic Business Process Management Systems
Marlon Dumas, Fredrik Milani, David Chapela-Campa
TL;DR
The paper addresses how BPM can evolve from automation to autonomy by leveraging agentic AI and process mining. It proposes an architectural vision for Agentic BPM Systems (A-BPMS), detailing a layered data-to-conversation architecture and a taxonomy of execution and orchestration patterns. It argues that empowering autonomous agents to sense, reason, and act within governance constraints can redefine process automation and governance boundaries. The work outlines research directions in process modelling, verification design, and redesign heuristics to maximize value from agentic capabilities.
Abstract
Since the early 90s, the evolution of the Business Process Management (BPM) discipline has been punctuated by successive waves of automation technologies. Some of these technologies enable the automation of individual tasks, while others focus on orchestrating the execution of end-to-end processes. The rise of Generative and Agentic Artificial Intelligence (AI) is opening the way for another such wave. However, this wave is poised to be different because it shifts the focus from automation to autonomy and from design-driven management of business processes to data-driven management, leveraging process mining techniques. This position paper, based on a keynote talk at the 2025 Workshop on AI for BPM, outlines how process mining has laid the foundations on top of which agents can sense process states, reason about improvement opportunities, and act to maintain and optimize performance. The paper proposes an architectural vision for Agentic Business Process Management Systems (A-BPMS): a new class of platforms that integrate autonomy, reasoning, and learning into process management and execution. The paper contends that such systems must support a continuum of processes, spanning from human-driven to fully autonomous, thus redefining the boundaries of process automation and governance.