Providing Domain Knowledge for Process Mining with ReWOO-Based Agents

Max W. Vogt; Peter van der Putten; Hajo A. Reijers

doi:10.1007/978-3-031-82225-4_49

Providing Domain Knowledge for Process Mining with ReWOO-Based Agents

Max W. Vogt, Peter van der Putten^*, Hajo A. Reijers

^*Corresponding author for this work

Sub Process Science

Leiden University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Process mining practitioners often face the challenge of interpreting complex process data and driving process improvements with limited expertise in process optimization, tools, and the application domain of the process. This study explores the integration of LLM-based agentic frameworks in process mining to bridge this gap and democratize access to process optimization. We developed a Proof-of-Concept that leverages a Reasoning WithOut Observation (ReWOO)-based agent to perform process discovery, problem identification, generate ecosystem domain knowledge, and propose potential process improvements. Our experiments on a range of business processes suggest that LLM-based agent systems can insert meaningful domain knowledge into process mining tool interactions.

Original language	English
Title of host publication	Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers
Editors	Andrea Delgado, Tijs Slaats
Publisher	Springer
Pages	663-676
Number of pages	14
ISBN (Electronic)	978-3-031-82225-4
ISBN (Print)	978-3-031-82224-7
DOIs	https://doi.org/10.1007/978-3-031-82225-4_49
Publication status	Published - 28 Mar 2025
Event	International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024 - Lyngby, Denmark Duration: 14 Oct 2024 → 18 Oct 2024

Publication series

Name	Lecture Notes in Business Information Processing
Volume	533
ISSN (Print)	1865-1348
ISSN (Electronic)	1865-1356

Conference

Conference	International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024
Country/Territory	Denmark
City	Lyngby
Period	14/10/24 → 18/10/24

Bibliographical note

Publisher Copyright:
© The Author(s) 2025.

Keywords

Agents
Domain knowledge
LLM
Process mining
ReWOO

Access to Document

10.1007/978-3-031-82225-4_49Licence: CC BY

978-3-031-82225-4_49Final published version, 2 MBLicence: CC BY

Cite this

Vogt, M. W., van der Putten, P., & Reijers, H. A. (2025). Providing Domain Knowledge for Process Mining with ReWOO-Based Agents. In A. Delgado, & T. Slaats (Eds.), Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers (pp. 663-676). (Lecture Notes in Business Information Processing; Vol. 533). Springer. https://doi.org/10.1007/978-3-031-82225-4_49

Vogt, Max W. ; van der Putten, Peter ; Reijers, Hajo A. / Providing Domain Knowledge for Process Mining with ReWOO-Based Agents. Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers. editor / Andrea Delgado ; Tijs Slaats. Springer, 2025. pp. 663-676 (Lecture Notes in Business Information Processing).

@inproceedings{ebfa4f9009b7430183e666e343d3649e,

title = "Providing Domain Knowledge for Process Mining with ReWOO-Based Agents",

abstract = "Process mining practitioners often face the challenge of interpreting complex process data and driving process improvements with limited expertise in process optimization, tools, and the application domain of the process. This study explores the integration of LLM-based agentic frameworks in process mining to bridge this gap and democratize access to process optimization. We developed a Proof-of-Concept that leverages a Reasoning WithOut Observation (ReWOO)-based agent to perform process discovery, problem identification, generate ecosystem domain knowledge, and propose potential process improvements. Our experiments on a range of business processes suggest that LLM-based agent systems can insert meaningful domain knowledge into process mining tool interactions.",

keywords = "Agents, Domain knowledge, LLM, Process mining, ReWOO",

author = "Vogt, {Max W.} and {van der Putten}, Peter and Reijers, {Hajo A.}",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.; International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024 ; Conference date: 14-10-2024 Through 18-10-2024",

year = "2025",

month = mar,

day = "28",

doi = "10.1007/978-3-031-82225-4_49",

language = "English",

isbn = "978-3-031-82224-7",

series = "Lecture Notes in Business Information Processing",

publisher = "Springer",

pages = "663--676",

editor = "Andrea Delgado and Tijs Slaats",

booktitle = "Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers",

}

Vogt, MW, van der Putten, P & Reijers, HA 2025, Providing Domain Knowledge for Process Mining with ReWOO-Based Agents. in A Delgado & T Slaats (eds), Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers. Lecture Notes in Business Information Processing, vol. 533, Springer, pp. 663-676, International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024, Lyngby, Denmark, 14/10/24. https://doi.org/10.1007/978-3-031-82225-4_49

Providing Domain Knowledge for Process Mining with ReWOO-Based Agents. / Vogt, Max W.; van der Putten, Peter; Reijers, Hajo A.
Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers. ed. / Andrea Delgado; Tijs Slaats. Springer, 2025. p. 663-676 (Lecture Notes in Business Information Processing; Vol. 533).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Providing Domain Knowledge for Process Mining with ReWOO-Based Agents

AU - Vogt, Max W.

AU - van der Putten, Peter

AU - Reijers, Hajo A.

N1 - Publisher Copyright: © The Author(s) 2025.

PY - 2025/3/28

Y1 - 2025/3/28

N2 - Process mining practitioners often face the challenge of interpreting complex process data and driving process improvements with limited expertise in process optimization, tools, and the application domain of the process. This study explores the integration of LLM-based agentic frameworks in process mining to bridge this gap and democratize access to process optimization. We developed a Proof-of-Concept that leverages a Reasoning WithOut Observation (ReWOO)-based agent to perform process discovery, problem identification, generate ecosystem domain knowledge, and propose potential process improvements. Our experiments on a range of business processes suggest that LLM-based agent systems can insert meaningful domain knowledge into process mining tool interactions.

AB - Process mining practitioners often face the challenge of interpreting complex process data and driving process improvements with limited expertise in process optimization, tools, and the application domain of the process. This study explores the integration of LLM-based agentic frameworks in process mining to bridge this gap and democratize access to process optimization. We developed a Proof-of-Concept that leverages a Reasoning WithOut Observation (ReWOO)-based agent to perform process discovery, problem identification, generate ecosystem domain knowledge, and propose potential process improvements. Our experiments on a range of business processes suggest that LLM-based agent systems can insert meaningful domain knowledge into process mining tool interactions.

KW - Agents

KW - Domain knowledge

KW - LLM

KW - Process mining

KW - ReWOO

UR - http://www.scopus.com/inward/record.url?scp=105002027734&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-82225-4_49

DO - 10.1007/978-3-031-82225-4_49

M3 - Conference contribution

AN - SCOPUS:105002027734

SN - 978-3-031-82224-7

T3 - Lecture Notes in Business Information Processing

SP - 663

EP - 676

BT - Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers

A2 - Delgado, Andrea

A2 - Slaats, Tijs

PB - Springer

T2 - International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024

Y2 - 14 October 2024 through 18 October 2024

ER -

Vogt MW, van der Putten P, Reijers HA. Providing Domain Knowledge for Process Mining with ReWOO-Based Agents. In Delgado A, Slaats T, editors, Process Mining Workshops - ICPM 2024 International Workshops, Lyngby, Denmark, October 14–18, 2024, Revised Selected Papers. Springer. 2025. p. 663-676. (Lecture Notes in Business Information Processing). doi: 10.1007/978-3-031-82225-4_49