# A Functional Software Reference Architecture for LLM-Integrated Systems

arXiv: https://arxiv.org/abs/2501.12904 · HTML: https://mlsanity.com/paper/2501.12904/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2025.

## Built on by (most cited first, 9 of 9)

- [Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy](https://mlsanity.com/paper/2602.05877/) (2026)
- [AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents](https://mlsanity.com/paper/2510.21031/) (2025)
- [LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis](https://mlsanity.com/paper/2601.05539/) (2026)
- [A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AI](https://mlsanity.com/paper/2510.26275/) (2025)
- [Specification and Detection of LLM Code Smells](https://mlsanity.com/paper/2512.18020/) (2025)
- [A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems](https://mlsanity.com/paper/2603.16325/) (2026)
- [RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems](https://mlsanity.com/paper/2603.28735/) (2026)
- [LLM Code Smells: A Taxonomy and Detection Approach](https://mlsanity.com/paper/2605.22976/) (2026)
- [Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods](https://mlsanity.com/paper/2607.17774/) (2026)

## Abstract (arXiv)

The integration of large language models into software systems is transforming capabilities such as natural language understanding, decision-making, and autonomous task execution. However, the absence of a commonly accepted software reference architecture hinders systematic reasoning about their design and quality attributes. This gap makes it challenging to address critical concerns like privacy, security, modularity, and interoperability, which are increasingly important as these systems grow in complexity and societal impact. In this paper, we describe our textitemerging results for a preliminary functional reference architecture as a conceptual framework to address these challenges and guide the design, evaluation, and evolution of large language model-integrated systems. We identify key architectural concerns for these systems, informed by current research and practice. We then evaluate how the architecture addresses these concerns and validate its applicability using three open-source large language model-integrated systems in computer vision, text processing, and coding.