Formal Foundations of Agentic Business Process Management

2026-04-19

AI Summary

Traditional business process management struggles to effectively model and govern collaborative processes driven by the objectives of multiple autonomous agents. This work proposes the first systematic formal framework for agent-driven business process management, wherein explicit goals are assigned to agents and organizational-level constraints—termed “guardrails”—are introduced at the strategy-selection layer to ensure controllable execution of multi-agent collaboration. Drawing upon formal methods, goal-oriented behavior theory, and game theory, we rigorously model and analyze four foundational problems within this paradigm across three representative settings. The resulting theoretical insights establish a solid foundation for the subsequent design and verification of agent-driven collaborative systems.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Game Theory and Economic Paradigms: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Just like traditional BPM systems, agentic BPM systems are built around a specification of the process under consideration. Their distinguishing feature, however, is that the execution of the process is driven by multiple autonomous decision-makers, referred to as agents. Since such agents cannot be fully controlled, the process specification is augmented with explicit objectives, or goals, assigned to the participating agents. Agents then pursue these goals, at least to the best of their efforts, under suitable assumptions on the behavior of others, by adopting appropriate strategies. Centrally, the organization enacting the process can use these specifications to provide guardrails on the decision-making capabilities of agents at the strategy level. This paper sets up the mathematical foundations of such systems in three key settings and analyzes four foundational problems of agentic BPM.

Problem

• Agentic BPM
• Autonomous agents
• Process specification
• Goal-oriented execution
• Strategy constraints

Innovation

• Agentic BPM
• autonomous agents
• goal-driven processes
• strategy-level guardrails
• formal foundations