NOMAD: A Multi-Agent LLM System for UML Class Diagram Generation from Natural Language Requirements

Abstract

Large Language Models (LLMs) are increasingly utilised in software engineering, yet their ability to generate structured artefacts such as UML diagrams remains underexplored. In this work, we present NOMAD, a cognitively inspired, modular multi-agent framework that decomposes UML generation into a series of rolespecialised subtasks. Each agent handles a distinct modelling activity, such as entity extraction, relationship classification, and diagram synthesis, mirroring the goal-directed reasoning processes of an engineer. This decomposition improves interpretability and allows for targeted verification strategies. We evaluate NOMAD through a mixed design: a large case study (Northwind) for in-depth probing and error analysis, and humanauthored UML exercises for breadth and realism. NOMAD outperforms all selected baselines, while revealing persistent challenges in fine-grained attribute extraction. Building on these observations, we introduce the first systematic taxonomy of errors in LLM-generated UML diagrams, categorising structural, relationship, and logical errors. Finally, we examine verification as a design probe, showing its mixed effects and outlining adaptive strategies as promising directions.