A Formal Framework for Declarative Agentic AI in Business Process Analysis

2026-06-13

AI Summary

This study addresses the lack of formal representation of relationships among agents, goals, and objects in existing business process modeling approaches, which hinders autonomous decision-making and dynamic adaptation. To bridge this gap, the paper proposes the AGO methodology, which uniquely integrates declarative agent-based AI with formal process modeling. Grounded in set theory and mathematical logic, AGO establishes a triadic formal framework centered on Agents, Goals, and Objects, structured as a Business Process Knowledge Base (BPKB). This knowledge base offers semantic precision and logical completeness, enabling structured querying, incremental evolution, and automated workflow generation, thereby providing an inferable and extensible knowledge foundation for intelligent business processes.

Abstract

Agentic AI opens new opportunities for automating Business Process (BP), enabling autonomous decision-making and dynamic adaptation. However, realising this potential requires BP entities and their interactions to be defined with formal precision. This paper presents a formal framework for Agentic BP analysis through the AGO methodology. AGO captures the modelling perspective in terms of who is acting (Agents), why it is carried out (Goals), and what the relevant entities are (Objects). Grounded in set theory and mathematical logic, we formally define the AGO entity types and their interactions, organising all definitions into a BP Knowledge Base (BPKB). The resulting BPKB supports structured querying, incremental updates, and automatic generation of BP workflows, while ensuring soundness and completeness of the derived paths.

Problem

• Agentic AI
• Business Process Analysis
• Formal Framework
• Entity Interaction
• Autonomous Decision-making

Innovation

• Agentic AI
• Formal Framework
• Business Process Analysis
• AGO Methodology
• Knowledge Base