Beyond Control-Flow: Integrating the Resource Perspective into Multi-Collaborative Process Modeling from Text

The creation of Business Process Model and Notation (BPMN) models is a complex and time-consuming task requiring both domain knowledge and proficiency in modeling conventions. Recent advances in large language models (LLMs) have significantly expanded the possibilities for generating BPMN models directly from natural language, building upon earlier text-to-process methods with enhanced capabilities in handling complex descriptions. However, there is a lack of systematic evaluations of LLM-generated process models. Current efforts either use LLM-as-a-judge approaches or do not consider established dimensions of model quality. To this end, we introduce BEF4LLM, a novel LLM evaluation framework comprising four perspectives: syntactic quality, pragmatic quality, semantic quality, and validity. Using BEF4LLM, we conduct a comprehensive analysis of open-source LLMs and benchmark their performance against human modeling experts. Results indicate that LLMs excel in syntactic and pragmatic quality, while humans outperform LLMs in semantic aspects; however, the differences in scores are relatively modest, highlighting LLMs' competitive potential despite challenges in validity and semantic quality. The insights highlight current strengths and limitations of using LLMs for BPMN modeling and guide future model development and fine-tuning. Addressing these areas is essential for advancing the practical deployment of LLMs in business process modeling.

The advent of Large Language Models (LLMs) has significantly transformed tasks across Software Engineering. In the context of Business Process Management, LLMs are now being explored as tools to derive process models directly from textual descriptions. Existing approaches range from chatbot-driven systems that assist with iterative, text-based modeling to fully automated end-to-end modeling assistants. However, we argue that process modeling is inherently complex and cannot be effectively addressed through black-box solutions. Instead, we envision modeling as an open-ended conversational activity, best supported by an interactive, iterative process involving both humans and LLM. In our approach, the modeling task is decomposed into smaller, manageable steps. Each step results in intermediate artifacts and explicitly documents the rationale behind each modeling decision. During this process, we incrementally uncover simple behavioral relations that guide the construction of the model. Given the current limitations of LLMs in reasoning about complex dependencies, we complement them with specialized tools developed in the field to structure process models based on behavioral relations. This hybrid approach enables the generation of sound, yet comprehensible models that evolve through transparent and explainable steps. In this paper, we present our research agenda and introduce Pragmos, a prototype system that operationalizes this vision. Pragmos demonstrates how LLMs can collaborate with human users as both domain and modeling experts to co-create evolving process models through a structured and explainable workflow.

Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data. Reinforcement learning (RL) can optimize beyond this ceiling using external quality measures, but how the reward function should be designed when quality is multi-dimensional remains unexplored. We present a systematic investigation of reward function design for RL-based process model generation, training two LLM families (Llama3.1 8B, Qwen2.5 14B) under 48 configurations using Group Sequence Policy Optimization with rewards derived from an automated evaluation framework comprising 38 metrics across syntactic, pragmatic, and semantic quality. Three findings emerge. First, RL significantly improves pragmatic and syntactic quality while preserving semantic fidelity, reducing output variability by more than sixfold. Second, equal reward weighting consistently outperforms targeted weighting: emphasizing a specific dimension fails to improve it and can collapse the model into a low-quality mode. Third, design choices interact with model architecture in non-trivial ways: the invalidity penalty is essential for one model but irrelevant for the other, and SFT initialization is indispensable for one architecture but counterproductive for another. These results demonstrate that reward composition is a primary determinant of optimization outcomes, with effects as large as the decision to apply RL itself. The findings generalize to any structured generation task where quality is assessed along multiple automated dimensions. We release our implementation and experimental code at https://github.com/chlauer99/RL_for_process_modeling.