With the recent success of large language models (LLMs), the idea of AI-augmented Business Process Management systems is becoming more feasible. One of their essential characteristics is the ability to be conversationally actionable, allowing humans to interact with the LLM effectively to perform crucial process life cycle tasks such as process model design and redesign. However, most current research focuses on single-prompt execution and evaluation of results, rather than on continuous interaction between the user and the LLM. In this work, we aim to explore the feasibility of using LLMs to empower domain experts in the creation and redesign of process models in an iterative and effective way. The proposed conversational process model redesign (CPMR) approach receives as input a process model and a redesign request by the user in natural language. Instead of just letting the LLM make changes, the LLM is employed to (a) identify process change patterns from literature, (b) re-phrase the change request to be aligned with an expected wording for the identified pattern (i.e. the meaning), and then to (c) apply the meaning of the change to the process model. This multi-step approach allows for explainable and reproducible changes. In order to ensure the feasibility of the CPMR approach, and to find out how well the patterns from literature can be handled by the LLM, we perform an extensive evaluation, also in comparison to a baseline approach without change patterns. The results show that some patterns are hard to understand by LLMs and by users and that clear change descriptions by users are essential. Overall, we recommend a hybrid approach that identifies all used change patterns and then directly applies those patterns that work correctly and for the others derives follow-up questions in order to improve user input.

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 view on business processes. This shift is driven by the realization of process awareness by agent-oriented abstractions: software and human agents act as primary functional entities that perceive, reason, and act within explicit process frames. Thus, APM moves away from automation-oriented BPM towards systems in which autonomy is constrained, aligned, and made operational through process aware agents. We introduce the core abstractions and architectural elements required to realize APM systems and elaborate on four key capabilities that agents in APM systems 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.

Agent system mining is a recently introduced type of process mining that takes a bottom-up approach to the data-driven analysis of socio-technical systems that execute business processes in organizations. Instead of the top-down approach used in conventional process mining that studies a system in terms of its global state evolution, agent system mining analyzes the system as if it is composed of autonomous agents, each with its local state and behavior, interacting with other agents and the environment to contribute to the emerging global behavior of the business process. Recently, Agent Miner, the first algorithm for discovering agent systems from event data generated by process-aware information systems, has been proposed. The quality of the agent systems discovered by this algorithm depends on the quality of the agent types (or agents), which are identified from the available information about agent instances in the data. In this paper, we study the suitability and benefits of using methods from the organizational mining subarea of process mining for identifying agent types. The experiments we conduct over real-world datasets confirm the usefulness of such methods for discovering simple, modular, and accurate agent systems. These conclusions are grounded in quality metrics such as the size of discovered models (simplicity), Louvain modularity and the Gini coefficient (modularity), and precision and recall (accuracy). The results confirm the benefits of using organizational mining for identifying agent types when discovering agent systems from event data, leading to the construction of models of superior quality in precision, recall, and simplicity compared to models constructed by state-of-the-art conventional process discovery algorithms.

A key concern of automatic process discovery is providing insights into business process performance. Process analysts are specifically interested in waiting times and delays for identifying opportunities to speed up processes. Against this backdrop, it is surprising that current techniques for automatic process discovery generate directly-follows graphs and comparable process models without representing the time axis explicitly. This paper presents four layout strategies for automatically constructing process models that explicitly align with a time axis. We exemplify our approaches for directly-follows graphs. We evaluate their effectiveness by applying them to real-world event logs with varying complexities. Our specific focus is on their ability to handle the trade-off between high control-flow abstraction and high consistency of temporal activity order. Our results show that timeline-based layouts provide benefits in terms of an explicit representation of temporal distances. They face challenges for logs with many repeating and concurrent activities.

Business process simulation (BPS) is a versatile technique for estimating process performance across various scenarios. Traditionally, BPS approaches employ a control-flow-first perspective by enriching a process model with simulation parameters. Although such approaches can mimic the behavior of centrally orchestrated processes, such as those supported by workflow systems, current control-flow-first approaches cannot faithfully capture the dynamics of real-world processes that involve distinct resource behavior and decentralized decision-making. Recognizing this issue, this paper introduces AgentSimulator, a resource-first BPS approach that discovers a multi-agent system from an event log, modeling distinct resource behaviors and interaction patterns to simulate the underlying process. Our experiments show that AgentSimulator achieves state-of-the-art simulation accuracy with significantly lower computation times than existing approaches while providing high interpretability and adaptability to different types of process-execution scenarios.

The so-called Internet of Things is of increasing importance for facilitating productivity across industries, i.e., by connecting sensors with manufacturing lines and IT system landscapes with an increasing degree of autonomy. In this context, a common challenge is enabling reasonable trade-offs between structure and control on the one hand and flexibility and human-like intelligent behavior on the other hand. To address this challenge, we establish the need for and requirements of a hybrid IoT-/agent-based business process orchestration architecture that utilizes open standards. We propose a four-layered architecture, which integrates autonomous agents and business process orchestration for IoT/agents, and provide a running example for a supply chain management (purchasing) use case.

Executing business processes in a decentralized manner can improve inter-organizational efficacy. For example, blockchain-based process execution allows, at least conceptually, for cross-organizational compatibility, data integration, and integrity assurance without the need for a centralized trusted operator. However, most business processes run in agile and rapidly changing business environments. Updating a decentralized process requires continuous and extensive consensus-building efforts. Reflecting all organizations' business requirements is hardly practicable. Hence, in many real-life scenarios, to support cases with initially unforeseen properties, organizations can allow to bypass the decentralized process and fall-back to local variants. Yet, the decision to bypass or update a given process can have significant social implications since it may encourage a social dynamic that encourages collective avoidance of the decentralized process. This paper proposes a multi-agent simulation system to assess the social consequences of approving a bypass under given conditions. The proposed simulation is intended to inform the decision-maker (human or machine) on whether to allow to bypass a process or not. Moreover, we present an architecture for the integration of multi-agent simulation system, local process engine, and decentralized process execution environment, and describe a possible implementation with a particular tool chain.