PMAx: An Agentic Framework for AI-Driven Process Mining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Antonov, Anton, Kourani, Humam, Berti, Alessandro, Park, Gyunam, van der Aalst, Wil M. P.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915867172798464
author Antonov, Anton
Kourani, Humam
Berti, Alessandro
Park, Gyunam
van der Aalst, Wil M. P.
author_facet Antonov, Anton
Kourani, Humam
Berti, Alessandro
Park, Gyunam
van der Aalst, Wil M. P.
contents Process mining provides powerful insights into organizational workflows, but extracting these insights typically requires expertise in specialized query languages and data science tools. Large Language Models (LLMs) offer the potential to democratize process mining by enabling business users to interact with process data through natural language. However, using LLMs as direct analytical engines over raw event logs introduces fundamental challenges: LLMs struggle with deterministic reasoning and may hallucinate metrics, while sending large, sensitive logs to external AI services raises serious data-privacy concerns. To address these limitations, we present PMAx, an autonomous agentic framework that functions as a virtual process analyst. Rather than relying on LLMs to generate process models or compute analytical results, PMAx employs a privacy-preserving multi-agent architecture. An Engineer agent analyzes event-log metadata and autonomously generates local scripts to run established process mining algorithms, compute exact metrics, and produce artifacts such as process models, summary tables, and visualizations. An Analyst agent then interprets these insights and artifacts to compile comprehensive reports. By separating computation from interpretation and executing analysis locally, PMAx ensures mathematical accuracy and data privacy while enabling non-technical users to transform high-level business questions into reliable process insights.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15351
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PMAx: An Agentic Framework for AI-Driven Process Mining
Antonov, Anton
Kourani, Humam
Berti, Alessandro
Park, Gyunam
van der Aalst, Wil M. P.
Artificial Intelligence
Multiagent Systems
Process mining provides powerful insights into organizational workflows, but extracting these insights typically requires expertise in specialized query languages and data science tools. Large Language Models (LLMs) offer the potential to democratize process mining by enabling business users to interact with process data through natural language. However, using LLMs as direct analytical engines over raw event logs introduces fundamental challenges: LLMs struggle with deterministic reasoning and may hallucinate metrics, while sending large, sensitive logs to external AI services raises serious data-privacy concerns. To address these limitations, we present PMAx, an autonomous agentic framework that functions as a virtual process analyst. Rather than relying on LLMs to generate process models or compute analytical results, PMAx employs a privacy-preserving multi-agent architecture. An Engineer agent analyzes event-log metadata and autonomously generates local scripts to run established process mining algorithms, compute exact metrics, and produce artifacts such as process models, summary tables, and visualizations. An Analyst agent then interprets these insights and artifacts to compile comprehensive reports. By separating computation from interpretation and executing analysis locally, PMAx ensures mathematical accuracy and data privacy while enabling non-technical users to transform high-level business questions into reliable process insights.
title PMAx: An Agentic Framework for AI-Driven Process Mining
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2603.15351