LLMA-UML: Extending the UML for Modeling LLM-Agent Systems
Open Access
- 4 October 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 310-319
Abstract
Large Language Model (LLM) agents are becoming important building blocks of software systems. However, an analysis of recent publications shows that existing modeling approaches for LLM-agent systems are fragmented and rarely grounded in widely adopted standards such as the Unified Modeling Language (UML). This fragmentation hinders communication, design review, and early architectural validation. After a review of existing modeling approaches, this paper introduces LLMA-UML, a UML profile with semantics for modeling LLM-agent systems. Designed as a lightweight yet semantically explicit modeling extension, it remains compatible with established UML-based workflows and enables model validation via constraints in the Object Constraint Language (OCL). The profile explicitly defines the boundaries of agents, including prompts, responses, context, memory, tools and retrieval. It also separates design-time specifications from runtime instances across UML diagrams. We describe the conceptual foundations and profile design of LLMA-UML and evaluate it through a representative case study. The results indicate that LLMA-UML improves the expressiveness and analyzability of UML models for LLM-based agent architectures.Keywords
Funding Information
- Bundesministerium für Forschung und Technologie (13IHS221B)
- Ministry of Economic Affairs, Industry, Climate Action and Energy of the State of North Rhine-Westphalia (EFRE-20800498)
This publication has 38 references indexed in Scilit:
- Security threat modeling for emerging AI-agent protocols: A comparative analysis of MCP, A2A, agora, and ANPJournal of Information Security and Applications, 2026
- One For All: LLM-based Heterogeneous Mission Planning in Precision AgricultureIFAC-PapersOnLine, 2025
- LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent ArchitecturesInformation Fusion, 2025
- Towards Modeling Human-Agentic Collaborative Workflows: A BPMN Extension2025
- An empirical evaluation of pre-trained large language models for repairing declarative formal specificationsEmpirical Software Engineering, 2025
- LLM-Based Agents for Automating the Enhancement of User Story Quality: An Early Report2024
- LLM Based Multi-agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domain2024
- Paving the Way for Implementing Multiagent Systems: Integrating Gaia with Agent-UML2006
- Agent Oriented Analysis Using Message/UML2002
- Representing Agent Interaction Protocols in UML2001