Large Language Models to Enhance Business Process Modeling: Past, Present, and Future Trends

2026-04-15 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Advanced, quick

Summary

A literature review examines AI-driven methods for transforming natural language into Business Process Model and Notation (BPMN) models, focusing on Large Language Models (LLMs). The analysis identifies a shift from rule-based and traditional Natural Language Processing (NLP) pipelines to LLM-based architectures utilizing prompt engineering, intermediate representations, and iterative refinement. While these LLM approaches enhance automated process model generation, the review highlights persistent challenges including semantic correctness, fragmented evaluation practices, reproducibility issues, and limited real-world validation. The study identifies key research gaps and future directions, such as integrating contextual knowledge via Retrieval-Augmented Generation (RAG) with LLMs, developing interactive modeling architectures, and establishing standardized evaluation frameworks.

Key takeaway

For NLP Engineers developing business process automation tools, this review indicates a clear trend towards LLM-based architectures. You should prioritize integrating Retrieval-Augmented Generation (RAG) to enhance contextual understanding and focus on developing robust, standardized evaluation frameworks to address current semantic correctness and reproducibility challenges in your solutions.

Key insights

LLMs are shifting business process modeling from rule-based systems to prompt-engineered, iterative refinement architectures.

Principles

• LLMs enhance automated process model generation.
• Contextual knowledge improves LLM-based modeling.

Method

The review followed a structured strategy to classify approaches, examine LLM integration in text-to-model pipelines, and investigate evaluation practices for generated models.

In practice

• Utilize prompt engineering for LLM-based BPMN generation.
• Employ iterative refinement in process model creation.

Topics

• Large Language Models
• Business Process Modeling
• BPMN
• Prompt Engineering
• Retrieval-Augmented Generation

Best for: NLP Engineer, AI Scientist, Research Scientist, Machine Learning Engineer

Related on AIssential

• Large Language Models to Enhance Business Process Modeling: Past, Present, and Future Trends — LLMs significantly advance text-to-BPMN generation but face challenges in semantic accuracy, evaluation, and real-world applicability.
• Retrieval-Augmented Generation as a Bridge Between Classical NLP Pipelines and Modern LLM Systems — Retrieval-augmented generation (RAG) addresses the limitation of static knowledge in large language models (LLMs) by connecting them to external, up-to-date knowledge sources.
• The Complete Guide to RAG: Why Retrieval-Augmented Generation Is the Backbone of Enterprise AI in… — RAG enables LLMs to access real-time external data, overcoming knowledge cutoffs and reducing hallucinations.
• IEEE Rolls Out Large Language Models Virtual Training Course — Large language models are fundamental architectural components demanding deep technical understanding for reliable and secure integration into digital infrastructures.
• Büyük Dil Modellerinin Hafızasını Güçlendiren Yaklaşım:Retrieval-Augmented Generation (RAG) — RAG enhances LLMs by providing external, real-time context, reducing hallucinations and improving factual accuracy.
• Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems — LLMs, especially with RAG and GraphRAG, can automate Design Structure Matrix generation for complex systems.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.