Theme, Goals, and Intended Audience

Theme

Generative AI has emerged as a powerful tool across various domains, and early prototypes in process mining have demonstrated its feasibility for tasks ranging from process analysis to automation. GenAI4PM 2025 will explore the next steps in this exciting field, focusing on advanced, systematic studies that:

Explore novel methodologies and evaluation frameworks for GenAI in process mining.
Integrate GenAI with complementary technologies (e.g., blockchain, RPA, BPM systems).
Evaluate the practical impact on business KPIs and process transformation.

Goals

Research Advancement: Encourage submissions that introduce new techniques, methodologies, and evaluation benchmarks for integrating GenAI in process mining.
Industry-Academia Synergy: Create a forum for practitioners and researchers to exchange insights, share case studies, and discuss implementation challenges.
Interdisciplinary Innovation: Stimulate discussion on combining GenAI with other advanced technologies, thus broadening the scope of process mining applications.
Community Building: Foster a collaborative environment that includes interactive sessions, a keynote address by an industry expert, and a concluding round-table to outline future directions.

Intended Audience

The workshop is targeted toward:

Researchers in process mining and AI,
Industry professionals implementing process analytics and automation,
Developers and tool providers focused on process mining applications,
Academics interested in the evolving role of generative AI in enterprise applications.

Call for Papers

Aims and Scope

Generative AI (GenAI) is a powerful tool for a multitude of activities, and prototypes implementing GenAI in process analyses have been recently proposed by industry and academia. However, while basic use cases are being covered, more advanced and systematic studies need to be discussed. Moreover, while prototypes have been implemented, their effectiveness in terms of improving a company’s KPIs was marginally discussed.

The GenAI4PM 2025 workshop aims to provide a premier platform for advancing the integration of generative AI within process mining. By fostering collaboration between academia and industry, we plan to stimulate innovative research and practical applications that address both current challenges and future opportunities in the field. We look forward to contributing to the rich combination of topics at ICPM 2025 and engaging a broad, interdisciplinary audience.

We invite submissions that explore diverse aspects of GenAI in process mining, including but not limited to:

Process Mining Tasks: Novel applications and techniques using GenAI.
Process Modeling: Innovative approaches using procedural, declarative, or mixed modeling.
Robotic Process Automation: Integration of GenAI with automation systems.
Implementation Strategies: Implementing GenAI-powered process mining solutions.
Evaluation Frameworks: Benchmarks, impact estimations, and quality frameworks.
Predictive Monitoring: Using GenAI to predict process deviations and bottlenecks.
Root-Cause Analysis: Leveraging AI-driven insights and detailed process analytics to identify, analyze, and address the underlying causes of inefficiencies, bottlenecks, compliance violations, or failures in business operations.
Challenges: Issues of using GenAI in process mining such as bias, fairness, and explainability.
Case Studies: Real-world applications and their outcomes.

Types of Contributions and Submission Guidelines

We invite authors to submit the following types of papers (all should follow the Springer LNBIP format, see FAQ for details):

Full Papers (up to 12 pages): Describing novel research methodologies or case studies performed in industry, to be published in the proceedings.
Implementation Papers (up to 9 pages): Illustrating a tool or implementation of GenAI in the context of process mining.
Visionary Papers (up to 9 pages): Discussing the future steps of GenAI4PM.

Full-length papers accepted (minimum 5 for a full-day workshop) will be published in the Springer LNBIP proceedings, with an acceptance rate capped at 50% as per Springer’s requirements. Additional papers or activities may be included pending negotiation and space availability.

Important Dates

Abstract Submission: July 18, 2025
Papers Submission: July 25, 2025
Paper Acceptance Notification: August 22, 2025
Pre-workshop Camera-Ready Papers: September 22, 2025
Workshops: October 20, 2025
Post-workshop Camera-Ready Papers: November 4, 2025

These dates are designed to allow sufficient time for authors to plan travel and finalize papers, including reformatting from IEEE to LNBIP for Springer proceedings.

Duration and Activities

Duration

We propose a full-day workshop (tentative) scheduled on October 20, 2025, the day prior to the main ICPM 2025 conference, ensuring ample time for both presentations and in-depth interactive sessions. The full-day duration is contingent on the acceptance of more than 5 full-length papers eligible for Springer proceedings; otherwise, it will be allocated half a day (two sessions).

Activities

Keynote Address: An industry or academic expert will outline the current state-of-the-art in GenAI applications within process mining, highlighting both achievements and challenges.
Paper Presentation Sessions:
- Full Papers (up to 12 pages): Showcasing novel research methodologies or case studies.
- Implementation Papers (up to 9 pages): Demonstrating tools or prototypes integrating GenAI with process mining.
- Visionary Papers (up to 9 pages): Discussing future directions and challenges in the field.
Each session will include a Q&A segment to foster discussion.
Interactive Discussions:
- Poster/Lightning-Talk Session: A brief, visual session to spark immediate feedback and ideas.
- Round-Table Discussion: Concluding session where all participants contribute to a collective vision for the evolution of GenAI in process mining.
Community Engagement: Pre-workshop online forums and social media channels will be used to promote early interactions and set the stage for a collaborative event.

Submissions

GenAI4PM 2024 received 19 submissions, of which 6 full papers and 3 short papers were accepted and presented at the workshop. For 2025, we aim to build on this success by encouraging high-quality submissions across all categories.

Potential Audience and Promotion

Potential Audience

Researchers and Academics: Experts in process mining, machine learning, and AI.
Industry Practitioners: Professionals implementing process improvements and digital transformations.
Tool Developers: Individuals and companies developing process mining tools with GenAI capabilities.
Cross-disciplinary Innovators: Those interested in the synergy between AI, blockchain, RPA, and other advanced technologies.

Promotion

Our promotion strategy includes:

A dedicated website: https://www.genai4pm2025.info/
Announcements via established mailing lists and social media channels.
Direct outreach to research groups, academic institutions, and industry partners.
Collaboration with workshop chairs and the steering committee to leverage their networks.

Organizers

Mohammadreza Fani Sani is an Applied and Data Scientist at Microsoft, focused on large language model solutions for Copilot AI and Process Mining, including task orchestration through Microsoft Copilot Studio. He earned his doctorate in the Process and Data Science (PADS) group at RWTH Aachen University, studying how data preprocessing can improve process mining outcomes. By blending his academic background with real-world experience, Mohammadreza continues to advance process mining through generative AI, robotic process automation, and other emerging AI technologies.

Cristina Cabanillas is a professor at the University of Seville, where she conducts research in the field of business process management and process mining. With a strong academic foundation, she has explored resource management and process optimization, contributing to both theoretical advancements and practical applications. Cristina has been actively involved in investigating how generative AI, particularly large language models, can enhance process mining techniques. Her work focuses on leveraging these models to improve process model discovery and analysis, enabling more intuitive and automated interpretations of complex process data. Through her publications and collaborations, Cristina is advancing the integration of generative AI into process mining, bridging the gap between cutting-edge AI technologies and real-world process improvement.

Humam Kourani is a Research Associate at the Fraunhofer Institute for Applied Information Technology (FIT). He is a member of the Center for Process Intelligence and contributes to research and software development projects within the Data Science and Artificial Intelligence Department. In addition, Humam serves as a process mining examiner for the Fraunhofer Personnel Certification Authority. Humam is currently pursuing his PhD at RWTH Aachen University. His research focuses on business process modeling, process discovery, and the integration of large language models into process mining.

Alessandro Berti is a Software Engineer at RWTH Aachen University, affiliated with the Process and Data Science (PADS) group. His doctoral thesis focuses on object-centric process mining. He plays a role as the main developer of pm4py, a leading Python library for process mining. Alessandro has made significant contributions to the integration of large language models within the pm4py framework. His work includes both development and research, with some publications that bridge the gap between large language models and the field of process mining.

Program Committee

The following members have accepted our invitation to join the Program Committee:

Akhil Kumar (Pennsylvania State University)
Amin Jalali (Stockholm University)
Andrea Burattin (Technical University of Denmark)
Andreas Oberweis (Karlsruhe Institute of Technology)
Andrey Rivkin (Technical University of Denmark)
Anna Kalenkova (The University of Adelaide)
Arik Senderovich (York University)
Barbara Weber (University of St. Gallen)
Boualem Benatallah (School of Computing, Dublin City University, Ireland)
Chiara Di Francescomarino (University of Trento)
David Chapela-Campa (University of Tartu)
Edyta Brzychczy (AGH University of Science and Technology)
Fareed Zandkarimi (SAP Signavio)
Flavia Santoro (UERJ)
Gabriel Marques Tavares (LMU Munich)
Gyunam Park (Fraunhofer Institute for Applied Information Technology (FIT))
Henrik Leopold (Kühne Logistics University)
Irene Vanderfeesten (KU Leuven)
István Koren (RWTH Aachen University, Chair of Process and Data Science)
Janik-Vasily Benzin (TU Munich)
Joseph Barjis (San Jose State University)
Julius Köpke (Universität Klagenfurt, Institute for Informatics Systems)
Kamil Żbikowski (Warsaw University of Technology)
Karolin Winter (Eindhoven University of Technology)
Luciana Barbieri (University of Campinas)
Majid Rafiei (SAP SE)
Manuel Resinas (University of Seville)
Marco Comuzzi (Ulsan National Institute of Science and Technology)
Marco Montali (KRDB Research Centre, Free University of Bozen-Bolzano)
Massimiliano de Leoni (Department of Mathematics - University of Padua)
Mathias Weske (HPI, University of Potsdam)
Matthias Weidlich (Humboldt-Universität zu Berlin)
Natalia Sidorova (Department of Mathematics and Computer Science, Technische Universiteit Eindhoven)
Nataliia Klievtsova (TU Munich)
Oliver Müller (Paderborn University)
Peter Fettke (Saarland University)
Peter van der Putten (LIACS, Leiden University and Pegasystems)
Pnina Soffer (University of Haifa)
Remco Dijkman (Eindhoven University of Technology)
Sander J.J. Leemans (RWTH Aachen)
Sandro Franzoi (University of Münster)
Seppe Vanden Broucke (Katholieke Universiteit Leuven)
Sylvain Hallé (University of St. Gallen)
Sven Weinzierl (FAU)
Thomas Hildebrandt (University of Copenhagen)
Timotheus Kampik (Umea University)
York Zisgen (University of Bayreuth)
Vinicius Stein Dani (Utrecht University)