pith. machine review for the scientific record. sign in

arxiv: 2603.18916 · v3 · submitted 2026-03-19 · 💻 cs.AI

Recognition: no theorem link

Agentic Business Process Management: A Research Manifesto

Diego Calvanese , Angelo Casciani , Giuseppe De Giacomo , Marlon Dumas , Fabiana Fournier , Timotheus Kampik , Emanuele La Malfa , Lior Limonad
show 10 more authors
Andrea Marrella Andreas Metzger Marco Montali Daniel Amyot Peter Fettke Artem Polyvyanyy Stefanie Rinderle-Ma Sebastian Sardi\~na Niek Tax Barbara Weber
Authors on Pith no claims yet

Pith reviewed 2026-05-15 08:21 UTC · model grok-4.3

classification 💻 cs.AI
keywords Agentic Business Process ManagementAPMBusiness Process ManagementAutonomous AgentsProcess AwarenessFramed AutonomyMulti-agent Systems
0
0 comments X

The pith

Business process management shifts to an agent-oriented model where autonomous agents perceive, reason, and act inside explicit process frames.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents Agentic Business Process Management as an extension of traditional BPM that treats software and human agents as the primary entities executing processes. It claims this marks a paradigm shift from automation-oriented views toward systems where autonomy is constrained and aligned through process awareness. Four capabilities—framed autonomy, explainability, conversational actionability, and self-modification—are introduced as the means to keep agent goals aligned with organizational goals while allowing proactive behavior. The manifesto maps out architectural elements and research challenges at the intersection of BPM, AI, and multi-agent systems to guide practical development.

Core claim

APM systems require agents that support framed autonomy, explainability, conversational actionability, and self-modification so that agents pursue organizational goals in a constrained yet proactive way inside explicit process frames, replacing the traditional process-centric abstraction with an agent-oriented one.

What carries the argument

The agent-oriented abstraction in which software and human agents serve as primary functional entities that perceive, reason, and act within explicit process frames.

If this is right

  • Process governance moves from fixed workflows to dynamic agent actions constrained by process frames.
  • Explainability becomes a required property of every agent decision within the process.
  • Agents gain the ability to modify their own behavior while remaining inside organizational process boundaries.
  • Conversational interfaces become the primary channel for directing and inspecting agent actions.
  • Research must advance jointly in BPM, AI, and multi-agent systems to realize the required capabilities.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Existing BPM tools will need redesign to expose process frames that agents can directly perceive and act upon.
  • New auditing mechanisms may emerge to verify that self-modifying agents stay within framed autonomy.
  • Organizations could test incremental rollout by equipping selected agents with subsets of the four capabilities first.

Load-bearing premise

The four capabilities of framed autonomy, explainability, conversational actionability, and self-modification can be jointly realized and will align agent goals with organizational goals without creating new failure modes.

What would settle it

An operational APM deployment in which agents equipped with all four capabilities still produce repeated goal misalignment or new failure modes that traditional BPM systems avoid.

Figures

Figures reproduced from arXiv: 2603.18916 by Andrea Marrella, Andreas Metzger, Angelo Casciani, Artem Polyvyanyy, Barbara Weber, Daniel Amyot, Diego Calvanese, Emanuele La Malfa, Fabiana Fournier, Giuseppe De Giacomo, Lior Limonad, Marco Montali, Marlon Dumas, Niek Tax, Peter Fettke, Sebastian Sardi\~na, Stefanie Rinderle-Ma, Timotheus Kampik.

Figure 1
Figure 1. Figure 1: Conceptual architecture of an APM system depicting its key actors, components (boxes), and [PITH_FULL_IMAGE:figures/full_fig_p007_1.png] view at source ↗
read the original abstract

This paper presents a manifesto that articulates the conceptual foundations of Agentic Business Process Management (APM), an extension of Business Process Management (BPM) for governing autonomous agents executing processes in organizations. From a management perspective, APM represents a paradigm shift from the traditional process view of the business process, driven by the realization of process awareness and an agent-oriented abstraction, where software and human agents act as primary functional entities that perceive, reason, and act within explicit process frames. This perspective marks a shift from traditional, automation-oriented BPM toward systems in which autonomy is constrained, aligned, and made operational through process awareness. We introduce the core abstractions and architectural elements required to realize APM systems and elaborate on four key capabilities that such APM agents must support: framed autonomy, explainability, conversational actionability, and self-modification. These capabilities jointly ensure that agents' goals are aligned with organizational goals and that agents behave in a framed yet proactive manner in pursuing those goals. We discuss the extent to which the capabilities can be realized and identify research challenges whose resolution requires further advances in BPM, AI, and multi-agent systems. The manifesto thus serves as a roadmap for bridging these communities and for guiding the development of APM systems in practice.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. This paper is a research manifesto proposing Agentic Business Process Management (APM) as an extension of traditional BPM. It claims a paradigm shift to an agent-oriented view in which software and human agents serve as primary entities that perceive, reason, and act inside explicit process frames. The manifesto defines four required capabilities for APM agents—framed autonomy, explainability, conversational actionability, and self-modification—asserting that these jointly align agent goals with organizational goals while preserving proactive yet constrained behavior, and it maps open research challenges at the intersection of BPM, AI, and multi-agent systems.

Significance. If the proposed abstractions prove workable, the manifesto could supply a useful organizing framework for research that integrates autonomous agents into organizational process governance. Its main contribution is the explicit enumeration of capabilities and the framing of their joint realization as an open challenge rather than a solved result; this prospective stance is appropriate for a manifesto and avoids overclaiming.

major comments (2)
  1. [Abstract] Abstract: the assertion that the four capabilities 'jointly ensure that agents' goals are aligned with organizational goals' is presented without any supporting derivation, model, or illustrative scenario showing necessity or sufficiency; while the text later treats realization as an open question, this phrasing is load-bearing for the central thesis.
  2. [Introduction and core abstractions] The introduction and core abstractions section: the claimed paradigm shift from a 'traditional process view' to an 'agent-oriented abstraction' is not accompanied by a precise contrast with existing BPM literature on agent-based or goal-oriented process models, leaving the novelty and distinctiveness of the framing difficult to evaluate.
minor comments (3)
  1. The manuscript would benefit from one or two concrete, even hypothetical, use-case sketches that show how the four capabilities interact in a single process instance.
  2. Terms such as 'process frames' and 'conversational actionability' are introduced without explicit definitions or pointers to related formalisms in the BPM or agent literature.
  3. The discussion of research challenges would be strengthened by indicating which challenges are primarily BPM problems, which are AI problems, and which require joint advances.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manifesto. The comments highlight opportunities to strengthen the presentation of our core claims and positioning relative to prior work. We address each point below and will incorporate revisions in the next version of the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the assertion that the four capabilities 'jointly ensure that agents' goals are aligned with organizational goals' is presented without any supporting derivation, model, or illustrative scenario showing necessity or sufficiency; while the text later treats realization as an open question, this phrasing is load-bearing for the central thesis.

    Authors: We agree that the abstract's phrasing risks implying a completed proof rather than a proposed framework. In the revision we will reword the abstract to state that the four capabilities are designed to jointly support alignment of agent goals with organizational objectives, while making explicit that their integrated realization remains an open research challenge (as already detailed in Sections 4 and 5). This preserves the manifesto's forward-looking character without overstating current results. revision: yes

  2. Referee: [Introduction and core abstractions] The introduction and core abstractions section: the claimed paradigm shift from a 'traditional process view' to an 'agent-oriented abstraction' is not accompanied by a precise contrast with existing BPM literature on agent-based or goal-oriented process models, leaving the novelty and distinctiveness of the framing difficult to evaluate.

    Authors: We accept that a sharper differentiation is needed. The revised introduction will include a new paragraph (or short subsection) that explicitly contrasts our agent-oriented abstraction—centered on framed autonomy inside explicit process frames—with prior agent-based BPM approaches, goal-oriented process modeling, and related frameworks in the BPM literature. We will cite representative works to clarify the distinct emphasis on the joint realization of the four capabilities as an organizing principle. revision: yes

Circularity Check

0 steps flagged

No significant circularity in definitional manifesto

full rationale

The paper is a research manifesto introducing APM as a conceptual extension of BPM, driven by process awareness and agent-oriented abstraction. It enumerates four capabilities (framed autonomy, explainability, conversational actionability, self-modification) as necessary elements for goal alignment but presents their joint realization explicitly as an open research challenge rather than a derived or proven result. No equations, formal derivations, predictions, fitted parameters, or load-bearing self-citations appear in the provided text. The argument is prospective and definitional, with no reduction of claims to inputs by construction. This is the expected outcome for a manifesto without technical derivations.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The manifesto rests on domain assumptions about agent capabilities and the sufficiency of process frames for alignment; no free parameters or invented physical entities are introduced.

axioms (2)
  • domain assumption Autonomous agents can be made to perceive, reason, and act within explicit process frames while remaining aligned with organizational goals.
    Stated in the abstract and introduction as the foundational premise of APM.
  • ad hoc to paper The four capabilities (framed autonomy, explainability, conversational actionability, self-modification) are jointly necessary and sufficient for practical APM systems.
    Introduced as the core requirements without independent justification or prior literature citation establishing sufficiency.
invented entities (1)
  • APM agent no independent evidence
    purpose: Primary functional entity that perceives, reasons, and acts inside process frames
    New abstraction introduced to replace traditional process-centric views; no independent evidence supplied beyond the manifesto itself.

pith-pipeline@v0.9.0 · 5586 in / 1501 out tokens · 42109 ms · 2026-05-15T08:21:27.881045+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. On the Hybrid Nature of ABPMS Process Frames and its Implications on Automated Process Discovery

    cs.AI 2026-04 unverdicted novelty 5.0

    ABPMS process frames are defined as hybrid semi-concurrent procedural and declarative models, with a proposed discovery method that maps declarative constraints into equivalent procedural fragments.

Reference graph

Works this paper leans on

86 extracted references · 86 canonical work pages · cited by 1 Pith paper · 3 internal anchors

  1. [1]

    Wooldridge, N

    M. Wooldridge, N. R. Jennings, Intelligent agents: Theory and practice, The knowledge engineering review 10 (2) (1995) 115–152.doi:10.1017/S0 269888900008122

    work page doi:10.1017/s0 1995

  2. [2]

    Y . Shen, X. Zhang, The impact of artificial intelligence on employment: the role of virtual agglomeration, Humanities and Social Sciences Communications 11 (1) (2024) 1–14.doi:10.1057/s41599-024-02647-9. 25

    work page doi:10.1057/s41599-024-02647-9 2024

  3. [3]

    J. He, C. Treude, D. Lo, LLM-based multi-agent systems for software engi- neering: Literature review, vision, and the road ahead, ACM Trans. Softw. Eng. Methodol. 34 (5) (2025) 124.doi:10.1145/3712003

    work page doi:10.1145/3712003 2025

  4. [4]

    Warren, Microsoft’s plan to fix the web with AI has already hit an embarrassing security flaw,The Verge, accessed: 2025-11-15 (Aug

    T. Warren, Microsoft’s plan to fix the web with AI has already hit an embarrassing security flaw,The Verge, accessed: 2025-11-15 (Aug. 2025). URLhttps://www.theverge.com/news/719617/microsoft-nlw eb-security-flaw-agentic-web

    work page 2025

  5. [5]

    Kampik, A

    T. Kampik, A. Mansour, O. Boissier, S. Kirrane, J. Padget, T. R. Payne, M. P. Singh, V . Tamma, A. Zimmermann, Governance of autonomous agents on the web: Challenges and opportunities, ACM Trans. Internet Technol. 22 (4) (2022) 104.doi:10.1145/3507910

    work page doi:10.1145/3507910 2022

  6. [6]

    Gabbay, J

    D. Gabbay, J. Horty, X. Parent, R. Van der Meyden, L. van der Torre, et al., Hand- book of Deontic Logic and Normative Systems, V olume 2, College Publications, 2021. URLhttps://www.collegepublications.co.uk/handbooks/?0 0005

    work page 2021

  7. [7]

    Shavit, S

    Y . Shavit, S. Agarwal, M. Brundage, S. Adler, C. O’Keefe, R. Campbell, T. Lee, P. Mishkin, T. Eloundou, A. Hickey, K. Slama, L. Ahmad, P. McMillan, A. Beutel, A. Passos, D. G. Robinson, Practices for governing agentic AI systems, OpenAI white paper, accessed: 2025-09-30 (Dec. 2023). URLhttps://cdn.openai.com/papers/practices-for-gover ning-agentic-ai-systems.pdf

    work page 2025

  8. [8]

    Weske, Business Process Management: Concepts, Languages, Architectures, Springer, 2024.doi:10.1007/978-3-662-69518-0

    M. Weske, Business Process Management: Concepts, Languages, Architectures, Springer, 2024.doi:10.1007/978-3-662-69518-0

    work page doi:10.1007/978-3-662-69518-0 2024

  9. [9]

    Dumas, M

    M. Dumas, M. La Rosa, J. Mendling, H. A. Reijers, Fundamentals of business process management, Springer, 2018.doi:10.1007/978-3-662-56509 -4

    work page doi:10.1007/978-3-662-56509 2018

  10. [10]

    H. Vu, N. Klievtsova, H. Leopold, S. Rinderle-Ma, T. Kampik, Agentic business process management: Practitioner perspectives on agent governance in business processes, in: Business Process Management: Responsible BPM Forum, Process Technology Forum, Educators Forum. BPM 2025, V ol. 565 of LNBIP, Springer, 2026, pp. 29–43.doi:10.1007/978-3-032-02936-2_3

    work page doi:10.1007/978-3-032-02936-2_3 2025

  11. [11]

    Decker, Design and analysis of process choreographies, Ph.D

    G. Decker, Design and analysis of process choreographies, Ph.D. thesis, Univer- sität Potsdam, Germany (2009). URLhttps://nbn-resolving.org/urn:nbn:de:kobv:517-opu s-40761

    work page 2009

  12. [12]

    A. Tour, A. Polyvyanyy, A. A. Kalenkova, A. Senderovich, Agent Miner: An algorithm for discovering agent systems from event data, in: Business Process Management, Springer, 2023, pp. 284–302.doi:10.1007/978-3-031-4 1620-0_17. 26

    work page doi:10.1007/978-3-031-4 2023

  13. [13]

    A. Tour, A. Polyvyanyy, A. A. Kalenkova, Agent system mining: Vision, benefits, and challenges, IEEE Access 9 (2021) 99480–99494.doi:10.1109/ACCESS .2021.3095464

    work page doi:10.1109/access 2021

  14. [14]

    Fournier, L

    F. Fournier, L. Limonad, Y . David, Agentic process observability: Discovering behavioral variability, in: Proceedings of the Process Management in the AI Era (PMAI 2025), V ol. 4087 of CEUR Workshop Proceedings, CEUR-WS.org, 2025, p. paper3. URLhttps://ceur-ws.org/Vol-4087

    work page 2025

  15. [15]

    Fettke, F

    P. Fettke, F. Fournier, L. Limonad, A. Metzger, S. Rinderle-Ma, B. Weber, XABPs: Towards explainable autonomous business processes, in: Proceedings of the Process Management in the AI Era (PMAI 2025), V ol. 4087 of CEUR Workshop Proceedings, CEUR-WS.org, 2025, p. paper2. URLhttps://ceur-ws.org/Vol-4087

    work page 2025

  16. [16]

    Calvanese, G

    D. Calvanese, G. De Giacomo, T. Kampik, Y . Lesperance, A. Marrella, A. Matta, et al., Autonomy in business process execution: Why we need first-class abstrac- tions for goals and normative frames, in: Proceedings of the Process Management in the AI Era (PMAI 2025), V ol. 4087 of CEUR Workshop Proceedings, CEUR- WS.org, 2025, p. paper6. URLhttps://ceur-ws...

    work page 2025

  17. [17]

    Montali, M

    M. Montali, M. Comuzzi, I. Teinemaa, D. Amyot, M. Dumas, Towards conversa- tional actionability in AI-augmented business process management systems, in: Proceedings of the Process Management in the AI Era (PMAI 2025), V ol. 4087 of CEUR Workshop Proceedings, CEUR-WS.org, 2025, p. paper8. URLhttps://ceur-ws.org/Vol-4087

    work page 2025

  18. [18]

    Elyasaf, A

    A. Elyasaf, A. Metzger, S. Sardina, A. Senderovich, E. S. Asensio, N. Tax, To- ward self-modifying autonomous business process systems, in: Proceedings of the Process Management in the AI Era (PMAI 2025), V ol. 4087 of CEUR Work- shop Proceedings, CEUR-WS.org, 2025, p. paper1. URLhttps://ceur-ws.org/Vol-4087

    work page 2025

  19. [19]

    Sapkota, K

    R. Sapkota, K. I. Roumeliotis, M. Karkee, AI agents vs. agentic AI: A conceptual taxonomy, applications and challenges, CoRR abs/2505.10468 (2025).arXiv: 2505.10468

    work page arXiv 2025

  20. [20]

    Wooldridge, An introduction to multiagent systems, 2nd Edition, John wiley & sons, 2009

    M. Wooldridge, An introduction to multiagent systems, 2nd Edition, John wiley & sons, 2009

    work page 2009

  21. [21]

    Amalfitano, A

    D. Amalfitano, A. Metzger, M. Autili, T. Fulcini, T. Hey, J. Keim, P. Pelliccione, V . Scotti, A. Koziolek, R. Mirandola, A. V ogelsang, A research roadmap for aug- menting software engineering processes and software products with generative AI (2025).arXiv:2510.26275

    work page arXiv 2025

  22. [22]

    N. R. Jennings, On agent-based software engineering, Artif. Intell. 117 (2) (2000) 277–296.doi:10.1016/S0004-3702(99)00107-1. 27

    work page doi:10.1016/s0004-3702(99)00107-1 2000

  23. [23]

    Dumas, F

    M. Dumas, F. Fournier, L. Limonad, A. Marrella, M. Montali, J.-R. Rehse, R. Ac- corsi, D. Calvanese, G. De Giacomo, D. Fahland, et al., AI-augmented business process management systems: a research manifesto, ACM Transactions on Man- agement Information Systems 14 (1) (2023) 1–19.doi:10.1145/3576047

    work page doi:10.1145/3576047 2023

  24. [24]

    Fettke, H.-G

    P. Fettke, H.-G. Fill, J. Köpcke, LLM, LAM, LxM agent: From talking to acting machines, Enterprise Modelling and Information Systems Architectures (EMISAJ) 20 (2025).doi:10.18417/emisa.20.3

    work page doi:10.18417/emisa.20.3 2025

  25. [25]

    Wooldridge, N

    M. Wooldridge, N. R. Jennings, D. Kinny, A methodology for agent-oriented analysis and design, in: Proceedings of the third annual conference on Au- tonomous Agents, 1999, pp. 69–76.doi:10.1145/301136.301165

    work page doi:10.1145/301136.301165 1999

  26. [26]

    Russell, P

    S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach (4th Edition), Pearson, 2020. URLhttp://aima.cs.berkeley.edu/

    work page 2020

  27. [27]

    H. Li, H. Zhang, A. E. Hassan, The rise of AI teammates in software engineering (SE) 3.0: How autonomous coding agents are reshaping software engineering, CoRR abs/2507.15003 (2025).arXiv:2507.15003

    work page arXiv 2025

  28. [28]

    Weber, Large language models as software components: A taxonomy for LLM- integrated applications (2024).arXiv:2406.10300

    I. Weber, Large language models as software components: A taxonomy for LLM- integrated applications (2024).arXiv:2406.10300

    work page arXiv 2024

  29. [29]

    A. E. Hassan, D. Lin, G. K. Rajbahadur, K. Gallaba, F. R. Côgo, B. Chen, H. Zhang, K. Thangarajah, G. A. Oliva, J. J. Lin, W. M. Abdullah, Z. M. J. Jiang, Rethinking software engineering in the era of foundation models: A curated cata- logue of challenges in the development of trustworthy FMware, in: M. d’Amorim (Ed.), Companion Proceedings of the 32nd AC...

    work page doi:10.1145/3663529.3663849 2024

  30. [30]

    Gabriel, G

    I. Gabriel, G. Keeling, A. Manzini, J. Evans, We need a new ethics for a world of AI agents, Nature 644 (2025). URLhttps://www.nature.com/articles/d41586-025-02454 -5

    work page 2025

  31. [31]

    Cassell, Embodied conversational agents: representation and intelligence in user interfaces, AI magazine 22 (4) (2001) 67–83.doi:10.1609/aimag.v2 2i4.1593

    J. Cassell, Embodied conversational agents: representation and intelligence in user interfaces, AI magazine 22 (4) (2001) 67–83.doi:10.1609/aimag.v2 2i4.1593

    work page doi:10.1609/aimag.v2 2001

  32. [32]

    T. Guo, X. Chen, Y . Wang, R. Chang, S. Pei, N. V . Chawla, O. Wiest, X. Zhang, Large language model based multi-agents: A survey of progress and challenges, in: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024, ijcai.org, 2024, pp. 8048–8057. URLhttps://www.ijcai.or...

    work page 2024

  33. [33]

    K. Tran, D. Dao, M. Nguyen, Q. Pham, B. O’Sullivan, H. D. Nguyen, Multi-agent collaboration mechanisms: A survey of LLMs, CoRR abs/2501.06322 (2025). arXiv:2501.06322

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  34. [34]

    Borgo, R

    S. Borgo, R. Ferrario, A. Gangemi, N. Guarino, C. Masolo, D. Porello, E. M. Sanfilippo, L. Vieu, DOLCE: A descriptive ontology for linguistic and cognitive engineering, Appl. Ontology 17 (1) (2022) 45–69.doi:10.3233/AO-21025 9

    work page doi:10.3233/ao-21025 2022

  35. [35]

    Loebe, P

    F. Loebe, P. Burek, H. Herre, GFO: the general formal ontology, Appl. Ontology 17 (1) (2022) 71–106.doi:10.3233/AO-220264

    work page doi:10.3233/ao-220264 2022

  36. [36]

    Franch, J

    X. Franch, J. C. Sampaio Leite, G. Mussbacher, J. Mylopoulos, A. Perini (Eds.), Social Modeling Using the i* Framework, Springer International Publishing, Cham, Switzerland, 2024.doi:10.1007/978-3-031-72107-6

    work page doi:10.1007/978-3-031-72107-6 2024

  37. [37]

    Giunchiglia, J

    F. Giunchiglia, J. Mylopoulos, A. Perini, The Tropos software development methodology: processes, models and diagrams, in: The First International Joint Conference on Autonomous Agents & Multiagent Systems, AAMAS 2002, ACM, 2002, pp. 35–36.doi:10.1145/544741.544748

    work page doi:10.1145/544741.544748 2002

  38. [38]

    A. S. Rao, M. P. Georgeff, BDI agents: From theory to practice, in: V . R. Lesser, L. Gasser (Eds.), Proceedings of the First International Conference on Multiagent Systems, June 12-14, 1995, San Francisco, California, USA, The MIT Press, 1995, pp. 312–319. URLhttps://cdn.aaai.org/ICMAS/1995/ICMAS95-042.pdf

    work page 1995

  39. [39]

    Poslad, P

    S. Poslad, P. Charlton, Standardizing agent interoperability: the FIPA approach, in: Mutli-Agents Systems and Applications, Springer-Verlag, 2001, pp. 98–117. doi:10.1007/3-540-47745-4_5

    work page doi:10.1007/3-540-47745-4_5 2001

  40. [40]

    P. N. Johnson-Laird, R. M. J. Byrne, Deduction, Psychology Press, 1991

    work page 1991

  41. [41]

    Saxena, S

    Y . Saxena, S. Chopra, A. M. Tripathi, Evaluating consistency and reasoning capabilities of large language models, in: 2024 Second International Confer- ence on Data Science and Information System (ICDSIS), 2024, pp. 1–5.doi: 10.1109/ICDSIS61070.2024.10594233

    work page doi:10.1109/icdsis61070.2024.10594233 2024

  42. [42]

    Khalid, A

    I. Khalid, A. M. Nourollah, S. Schockaert, Large language and reasoning mod- els are shallow disjunctive reasoners, in: W. Che, J. Nabende, E. Shutova, M. T. Pilehvar (Eds.), Proceedings of the 63rd Annual Meeting of the Asso- ciation for Computational Linguistics (V olume 1: Long Papers), Association for Computational Linguistics, Vienna, Austria, 2025, ...

    work page doi:10.18653/v1/2025.acl-long.433 2025

  43. [43]

    Acitelli, A

    G. Acitelli, A. Alman, F. M. Maggi, A. Marrella, Achieving framed autonomy in AI-augmented business process management systems through automated plan- ning, Inf. Syst. 133 (2025) 102573.doi:10.1016/j.is.2025.102573. 29

    work page doi:10.1016/j.is.2025.102573 2025

  44. [44]

    G. Amit, F. Fournier, S. Gur, L. Limonad, Model-informed lime extension for business process explainability, in: PMAI@IJCAI’22, V ol. 3310 of CEUR Work- shop Proceedings, CEUR-WS.org, 2022, p. paper1. URLhttps://ceur-ws.org/Vol-3310

    work page 2022

  45. [45]

    G. Amit, F. Fournier, L. Limonad, I. Skarbovsky, Situation-aware explainability for business processes enabled by complex events, in: BPM-W 2022, V ol. 460 of LNBIP, Springer, 2022, pp. 45–57.doi:10.1007/978-3-031-25383-6 _5

    work page doi:10.1007/978-3-031-25383-6 2022

  46. [46]

    Fahland, F

    D. Fahland, F. Fournier, L. Limonad, I. Skarbovsky, A. J. E. Swevels, How well can large language models explain business processes as perceived by users?, Data & Knowledge Engineering 157 (2025) 102416.doi:10.1016/j.data k.2025.102416

    work page doi:10.1016/j.data 2025

  47. [47]

    Fournier, L

    F. Fournier, L. Limonad, I. Skarbovsky, Y . David, The WHY in business pro- cesses: Discovery of causal execution dependencies, Künstliche Intelligenz 39 (2025) 197–219.doi:10.1007/s13218-024-00883-4

    work page doi:10.1007/s13218-024-00883-4 2025

  48. [48]

    David, F

    Y . David, F. Fournier, L. Limonad, I. Skarbovsky, The WHY in business pro- cesses: Unification of causal process models, in: Business Process Management Forum, Springer Nature Switzerland, 2026, pp. 40–57.doi:10.1007/978-3 -032-02929-4_3

    work page doi:10.1007/978-3 2026

  49. [49]

    Weyns, An introduction to self-adaptive systems: A contemporary software engineering perspective, John Wiley & Sons, 2020.doi:10.1002/978111 9574910

    D. Weyns, An introduction to self-adaptive systems: A contemporary software engineering perspective, John Wiley & Sons, 2020.doi:10.1002/978111 9574910

    work page doi:10.1002/978111 2020

  50. [50]

    A. Palm, A. Metzger, K. Pohl, Online reinforcement learning for self-adaptive information systems, in: S. Dustdar, E. Yu, C. Salinesi, D. Rieu, V . Pant (Eds.), Advanced Information Systems Engineering - 32nd International Con- ference, CAiSE 2020, V ol. 12127 of LNCS, Springer, 2020, pp. 169–184.doi: 10.1007/978-3-030-49435-3_11

    work page doi:10.1007/978-3-030-49435-3_11 2020

  51. [51]

    Metzger, T

    A. Metzger, T. Kley, A. Rothweiler, K. Pohl, Automatically reconciling the trade- off between prediction accuracy and earliness in prescriptive business process monitoring, Inf. Syst. 118 (2023) 102254.doi:10.1016/J.IS.2023.10 2254

    work page doi:10.1016/j.is.2023.10 2023

  52. [52]

    Rinderle, M

    S. Rinderle, M. Reichert, P. Dadam, Correctness criteria for dynamic changes in workflow systems - a survey, Data Knowl. Eng. 50 (1) (2004) 9–34.doi: 10.1016/J.DATAK.2004.01.002

    work page doi:10.1016/j.datak.2004.01.002 2004

  53. [53]

    Weber, M

    B. Weber, M. Reichert, S. Rinderle-Ma, W. Wild, Providing integrated life cycle support in process-aware information systems, Int. J. Cooperative Inf. Syst. 18 (1) (2009) 115–165.doi:10.1142/S0218843009001999

    work page doi:10.1142/s0218843009001999 2009

  54. [54]

    Marron, L

    A. Marron, L. Limonad, S. Pollack, D. Harel, Expecting the unexpected: de- veloping autonomous-system design principles for reacting to unpredicted events 30 and conditions, in: Proceedings of the IEEE/ACM 15th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS ’20, ACM New York, USA, 2020, p. 167–173.doi:10.1145...

    work page doi:10.1145/3387939.3391 2020

  55. [55]

    Di Ciccio, M

    C. Di Ciccio, M. Montali, Declarative process specifications: Reasoning, dis- covery, monitoring, in: W. M. P. van der Aalst, J. Carmona (Eds.), Process Mining Handbook, V ol. 448 of LNBIP, Springer, Cham, 2022, pp. 108–152. doi:10.1007/978-3-031-08848-3_4

    work page doi:10.1007/978-3-031-08848-3_4 2022

  56. [56]

    Kampik, C

    T. Kampik, C. Okulmus, Expressive power and complexity results for SIGNAL, an industry-scale process query language, in: BPM 2024 Forum, V ol. 526 of LNBIP, Springer, 2024, pp. 3–19.doi:10.1007/978-3-031-70418-5 _1

    work page doi:10.1007/978-3-031-70418-5 2024

  57. [57]

    Casciani, S

    A. Casciani, S. Agostinelli, Y . Lespérance, A. Marrella, S. Sardiña, Formal se- mantics for knowledge representation and automated reasoning in bpmn process models, Information Systems 140 (2026) 102718.doi:https://doi.org/ 10.1016/j.is.2026.102718

    work page doi:10.1016/j.is.2026.102718 2026

  58. [58]

    Mehdiyev, P

    N. Mehdiyev, P. Fettke, Explainable artificial intelligence for process mining: A general overview and application of a novel local explanation approach for predictive process monitoring, in: Interpretable AI: A Perspective of Granular Computing, Springer, 2021, pp. 1–18.doi:10.1007/978-3-030-64949 -4_1

    work page doi:10.1007/978-3-030-64949 2021

  59. [59]

    Kampik, C

    T. Kampik, C. Warmuth, A. Rebmann, R. Agam, L. Egger, A. Gerber, J. Hoffart, J. Kolk, P. Herzig, G. Decker, H. van der Aa, A. Polyvyanyy, S. Rinderle-Ma, I. Weber, M. Weidlich, Large process models: A vision for business process man- agement in the age of generative AI, KI - Künstliche Intelligenz 39 (2024) 81–95. doi:10.1007/s13218-024-00863-8

    work page doi:10.1007/s13218-024-00863-8 2024

  60. [60]

    L. F. Das Neves, C. Zerva, A. Gianola, A proposal for handling query ambiguity for process mining tasks, in: Proceedings of the 7th International Workshop on Artificial Intelligence and Formal Verification, Logic, Automata, and Synthesis (OVERLAY 2025), CEUR, 2025, p. n/a

    work page 2025

  61. [61]

    M. L. Bernardi, A. Casciani, M. Cimitile, A. Marrella, Conversing with business process-aware large language models: the BPLLM framework, J. Intell. Inf. Syst. 62 (6) (2024) 1607–1629.doi:10.1007/S10844-024-00898-1

    work page doi:10.1007/s10844-024-00898-1 2024

  62. [62]

    Klievtsova, J

    N. Klievtsova, J. Benzin, T. Kampik, J. Mangler, S. Rinderle-Ma, Conversational process modelling: State of the art, applications, and implications in practice, in: C. D. Francescomarino, A. Burattin, C. Janiesch, S. Sadiq (Eds.), Business Pro- cess Management Forum - BPM 2023 Forum, Utrecht, The Netherlands, Septem- ber 11-15, 2023, Proceedings, V ol. 49...

    work page doi:10.1007/978-3-031-416 2023

  63. [63]

    Klievtsova, J

    N. Klievtsova, J. Mangler, T. Kampik, S. Rinderle-Ma, Utilizing process models in the requirements engineering process through model2text transformation, in: G. Liebel, I. Hadar, P. Spoletini (Eds.), 32nd IEEE International Requirements Engineering Conference, RE 2024, Reykjavik, Iceland, June 24-28, 2024, IEEE, 2024, pp. 205–217.doi:10.1109/RE59067.2024.00028

    work page doi:10.1109/re59067.2024.00028 2024

  64. [64]

    Hendrickx, L

    K. Hendrickx, L. Perini, D. Van der Plas, W. Meert, J. Davis, Machine learning with a reject option: A survey, Machine Learning 113 (5) (2024) 3073–3110. doi:10.1007/s10994-024-06534-x

    work page doi:10.1007/s10994-024-06534-x 2024

  65. [65]

    Dwivedi, D

    R. Dwivedi, D. Dave, H. Naik, S. Singhal, R. Omer, P. Patel, B. Qian, Z. Wen, T. Shah, G. Morgan, et al., Explainable AI (XAI): Core ideas, techniques, and solutions, ACM Computing Surveys 55 (9) (2023) 1–33.doi:10.1145/35 61048

    work page doi:10.1145/35 2023

  66. [66]

    Sreedharan, A

    S. Sreedharan, A. Kulkarni, S. Kambhampati, Explainable human-AI interaction, Synthesis lectures on artificial intelligence and machine learning, Springer Inter- national Publishing, Cham, Switzerland, 2022.doi:10.1007/978-3-031 -03767-2

    work page doi:10.1007/978-3-031 2022

  67. [67]

    R. T. Marler, J. S. Arora, Survey of multi-objective optimization methods for engineering, Structural and multidisciplinary optimization 26 (2004) 369–395. doi:10.1007/s00158-003-0368-6

    work page doi:10.1007/s00158-003-0368-6 2004

  68. [68]

    Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

    L. Zheng, W.-L. Chiang, Y . Sheng, S. Zhuang, Z. Wu, Y . Zhuang, Z. Lin, Z. Li, D. Li, E. Xing, et al., Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena, Advances in Neural Information Processing Systems 36 (2023) 46595– 46623.doi:10.48550/arXiv.2306.05685

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2306.05685 2023

  69. [69]

    Kossen, S

    J. Kossen, S. Farquhar, Y . Gal, T. Rainforth, Active testing: Sample-efficient model evaluation, in: International Conference on Machine Learning, V ol. 139, PMLR, 2021, pp. 5753–5763. URLhttps://proceedings.mlr.press/v139/kossen21a.html

    work page 2021

  70. [70]

    Sammodi, A

    O. Sammodi, A. Metzger, X. Franch, M. Oriol, J. Marco, K. Pohl, Usage-based online testing for proactive adaptation of service-based applications, in: Proceed- ings of the 35th Annual IEEE International Computer Software and Applications Conference, COMPSAC 2011, Munich, Germany, 18-22 July 2011, IEEE Com- puter Society, 2011, pp. 582–587.doi:10.1109/COMP...

    work page doi:10.1109/compsac.2011.81 2011

  71. [71]

    Dragan, A

    P.-A. Dragan, A. Metzger, K. Pohl, Coordinated online reinforcement learning for self-adaptive systems using factored Q-Learning, in: 6th IEEE International Conference on Autonomic Computing and Self-Organizing Systems - ACSOS 2025, IEEE CS, USA, 2025, pp. 76–87.doi:10.1109/ACSOS66086.202 5.00024

    work page doi:10.1109/acsos66086.202 2025

  72. [72]

    Shoham, K

    Y . Shoham, K. Leyton-Brown, Multiagent Systems: Algorithmic, Game- Theoretic, and Logical Foundations, Cambridge University Press, Cambridge, UK, 2008.doi:10.1017/CBO9780511811654. 32

    work page doi:10.1017/cbo9780511811654 2008

  73. [73]

    Satyal, I

    S. Satyal, I. Weber, H.-y. Paik, C. Di Ciccio, J. Mendling, Business process im- provement with the AB-BPM methodology, Information Systems 84 (2019) 283– 298.doi:10.1016/j.is.2018.06.007

    work page doi:10.1016/j.is.2018.06.007 2019

  74. [74]

    Hüllermeier, W

    E. Hüllermeier, W. Waegeman, Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods, Machine learning 110 (3) (2021) 457–506.doi:10.1007/s10994-021-05946-3

    work page doi:10.1007/s10994-021-05946-3 2021

  75. [75]

    Nguyen, M

    V .-L. Nguyen, M. H. Shaker, E. Hüllermeier, How to measure uncertainty in un- certainty sampling for active learning, Machine Learning 111 (1) (2022) 89–122. doi:10.1007/s10994-021-06003-9

    work page doi:10.1007/s10994-021-06003-9 2022

  76. [76]

    Tharwat, W

    A. Tharwat, W. Schenck, A survey on active learning: State-of-the-art, practical challenges and research directions, Mathematics 11 (4) (2023) 820.doi:10.3 390/math11040820

    work page 2023

  77. [77]

    Metzger, T

    A. Metzger, T. Kley, A. Palm, Triggering proactive business process adapta- tions via online reinforcement learning, in: D. Fahland, C. Ghidini, J. Becker, M. Dumas (Eds.), Business Process Management - 18th International Confer- ence, BPM 2020, V ol. 12168 of LNCS, Springer, 2020, pp. 273–290.doi: 10.1007/978-3-030-58666-9_16

    work page doi:10.1007/978-3-030-58666-9_16 2020

  78. [78]

    Torra, M

    V . Torra, M. Bras-Amorós, Memory poisoning and secure multi-agent systems (2026).arXiv:2603.20357. URLhttps://arxiv.org/abs/2603.20357

    work page arXiv 2026

  79. [79]

    Beurer-Kellner, B

    L. Beurer-Kellner, B. Buesser, A. Cretu, E. Debenedetti, D. Dobos, D. Fabian, M. Fischer, D. Froelicher, K. Grosse, D. Naeff, E. Ozoani, A. Paverd, F. Tramèr, V . V olhejn, Design patterns for securing LLM agents against prompt injections, CoRR abs/2506.08837 (2025).arXiv:2506.08837,doi:10.48550/ARX IV.2506.08837

    work page doi:10.48550/arx 2025

  80. [80]

    J. L. Cobo-Ariza, J. Arregui, A. M. R. Quintero, Á. J. Varela-Vaca, M. T. Gómez-López, Explaining the compliance of security policies for GDPR in busi- ness processes, in: Advanced Information Systems Engineering Workshops - CAiSE 2025 Workshops, Vienna, Austria, June 16-20, 2025, Proceedings, Lec- ture Notes in Business Information Processing, Springer, ...

    work page doi:10.1007/978-3-031-94931-9 2025

Showing first 80 references.