---
_id: '65626'
abstract:
- lang: eng
  text: Business Process Management (BPM) is evolving rapidly. Building on a rich
    research portfolio that spans from early workflow automation to robotic process
    automation (RPA), large language models (LLMs) are the most recent disruptive
    technologies to influence all BPM capability areas. Particularly, these technologies
    fuel the emerging research fields of AI-enhanced business process management systems
    and autonomous process execution. In a design science research approach, we develop
    a modular LLM agent architecture that effectively enables the adaptation and execution
    of business processes. The architecture integrates a Frame Agent that can generate
    process descriptions and an Operational Agent that autonomously executes processes
    based on the Frame Agent’s process descriptions. It further enables a future Tactical
    Agent for autonomous process adaptations. We demonstrate the architecture’s applicability
    and utility with the real-world case of a meter-to-cash process, comparing it
    to the performance of an RPA bot. Our findings provide early insights into the
    challenges faced by autonomous process execution and its relation with RPA in
    terms of adaptability, flexibility, and complexity in autonomous process execution.
    While researchers can build on our findings to establish modular LLM-agent architectures
    for autonomous process execution, practitioners can derive early insights into
    the design of LLM agents for process automation.
article_number: '102748'
article_type: original
author:
- first_name: Alexander Marcus
  full_name: Skolik, Alexander Marcus
  id: '92908'
  last_name: Skolik
  orcid: 0009-0006-2519-1765
- first_name: Sascha Benjamin
  full_name: Kaltenpoth, Sascha Benjamin
  id: '50640'
  last_name: Kaltenpoth
- first_name: Daniel
  full_name: Beverungen, Daniel
  id: '59677'
  last_name: Beverungen
- first_name: Oliver
  full_name: Müller, Oliver
  id: '72849'
  last_name: Müller
citation:
  ama: Skolik AM, Kaltenpoth SB, Beverungen D, Müller O. A modular large language
    model agent architecture for adaptive and autonomous process-aware execution.
    <i>Information Systems</i>. 2026;141. doi:<a href="https://doi.org/10.1016/j.is.2026.102748">10.1016/j.is.2026.102748</a>
  apa: Skolik, A. M., Kaltenpoth, S. B., Beverungen, D., &#38; Müller, O. (2026).
    A modular large language model agent architecture for adaptive and autonomous
    process-aware execution. <i>Information Systems</i>, <i>141</i>, Article 102748.
    <a href="https://doi.org/10.1016/j.is.2026.102748">https://doi.org/10.1016/j.is.2026.102748</a>
  bibtex: '@article{Skolik_Kaltenpoth_Beverungen_Müller_2026, title={A modular large
    language model agent architecture for adaptive and autonomous process-aware execution},
    volume={141}, DOI={<a href="https://doi.org/10.1016/j.is.2026.102748">10.1016/j.is.2026.102748</a>},
    number={102748}, journal={Information Systems}, publisher={Elsevier BV}, author={Skolik,
    Alexander Marcus and Kaltenpoth, Sascha Benjamin and Beverungen, Daniel and Müller,
    Oliver}, year={2026} }'
  chicago: Skolik, Alexander Marcus, Sascha Benjamin Kaltenpoth, Daniel Beverungen,
    and Oliver Müller. “A Modular Large Language Model Agent Architecture for Adaptive
    and Autonomous Process-Aware Execution.” <i>Information Systems</i> 141 (2026).
    <a href="https://doi.org/10.1016/j.is.2026.102748">https://doi.org/10.1016/j.is.2026.102748</a>.
  ieee: 'A. M. Skolik, S. B. Kaltenpoth, D. Beverungen, and O. Müller, “A modular
    large language model agent architecture for adaptive and autonomous process-aware
    execution,” <i>Information Systems</i>, vol. 141, Art. no. 102748, 2026, doi:
    <a href="https://doi.org/10.1016/j.is.2026.102748">10.1016/j.is.2026.102748</a>.'
  mla: Skolik, Alexander Marcus, et al. “A Modular Large Language Model Agent Architecture
    for Adaptive and Autonomous Process-Aware Execution.” <i>Information Systems</i>,
    vol. 141, 102748, Elsevier BV, 2026, doi:<a href="https://doi.org/10.1016/j.is.2026.102748">10.1016/j.is.2026.102748</a>.
  short: A.M. Skolik, S.B. Kaltenpoth, D. Beverungen, O. Müller, Information Systems
    141 (2026).
date_created: 2026-05-14T11:19:08Z
date_updated: 2026-10-08T11:01:24Z
ddc:
- '000'
doi: 10.1016/j.is.2026.102748
file:
- access_level: closed
  content_type: application/pdf
  creator: dabe
  date_created: 2026-10-08T11:00:19Z
  date_updated: 2026-10-08T11:00:19Z
  file_id: '67435'
  file_name: IS - Autonomous Process Execution.pdf
  file_size: 1988723
  relation: main_file
  success: 1
file_date_updated: 2026-10-08T11:00:19Z
has_accepted_license: '1'
intvolume: '       141'
keyword:
- Business process management
- Large language models
- Modular agent architecture
- Autonomous process execution
- AI-augmented business process management systems
language:
- iso: eng
main_file_link:
- open_access: '1'
oa: '1'
publication: Information Systems
publication_identifier:
  issn:
  - 0306-4379
publication_status: published
publisher: Elsevier BV
quality_controlled: '1'
related_material:
  link:
  - relation: confirmation
    url: https://www.sciencedirect.com/science/article/pii/S0306437926000621?via%3Dihub
status: public
title: A modular large language model agent architecture for adaptive and autonomous
  process-aware execution
type: journal_article
user_id: '59677'
volume: 141
year: '2026'
...