Re-Thinking Process Mining in the AI-Based Agents Era

arXiv (Cornell University)

Abstract

Large Language Models (LLMs) have emerged as powerful conversational interfaces, and their application in process mining (PM) tasks has shown promising results. However, state-of-the-art LLMs struggle with complex scenarios that demand advanced reasoning capabilities. In the literature, two primary approaches have been proposed for implementing PM using LLMs: providing textual insights based on a textual abstraction of the process mining artifact, and generating code executable on the original artifact. This paper proposes utilizing the AI-Based Agents Workflow (AgWf) paradigm to enhance the effectiveness of PM on LLMs. This approach allows for: i) the decomposition of complex tasks into simpler workflows, and ii) the integration of deterministic tools with the domain knowledge of LLMs. We examine various implementations of AgWf and the types of AI-based tasks involved. Additionally, we discuss the CrewAI implementation framework and present examples related to process mining.

Authors 5

1. Alessandro Berti Aachen Process and Data Science Chair

   Fraunhofer Institute for Applied Information Technology · RWTH Aachen University

   Affiliation as printed

   Fraunhofer FIT , Sankt Augustin , Germany

   Process and Data Science Chair , RWTH Aachen University , Aachen , Germany

2. Mayssa Maatallah

   University of Sousse

   Affiliation as printed

   Higher Institute of Management of Sousse , University of Sousse , Sousse , Tunisia

3. Urszula Jessen

   Clinical Insights · Eindhoven University of Technology

   Affiliation as printed

   Eindhoven University of Technology , The Netherlands

   Process Insights , ECE Group Services , Hamburg , Germany

4. Michal Sroka

   Microsoft (United States)

   Affiliation as printed

   Microsoft

5. Sonia Ayachi Ghannouchi

   University of Sousse

   Affiliation as printed

   Higher Institute of Management of Sousse , University of Sousse , Sousse , Tunisia