Pragmos: A Process Agentic Modeling System
Pedro-Aar\'on Hern\'andez-\'Avalos, Luciano Garc\'ia-Ba\~nuelos

TL;DR
Pragmos introduces a hybrid, interactive system leveraging LLMs and specialized tools to collaboratively and transparently develop business process models through iterative, explainable steps.
Contribution
The paper presents Pragmos, a novel process modeling system that combines LLMs with domain-specific tools for collaborative, transparent, and iterative process model creation.
Findings
Pragmos enables co-creation of process models with human users.
The system produces sound, comprehensible models through incremental steps.
It demonstrates effective collaboration between LLMs and specialized tools.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
