A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems

Marcos Galdino; Johanna Grahl; Tobias Hamann; Anas Abdelrazeq; Ingrid Isenhardt

cs.SEMar 17, 2026

A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems

Authors: Marcos Galdino, Johanna Grahl, Tobias Hamann, Anas Abdelrazeq, Ingrid Isenhardt

Organizations: IQS Intelligence in Quality Sensing, Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University, RWTH Aachen University, Aachen, Germany

Abstract

Large Language Models-Cognitive Assistants (LLM-CAs) can enhance Quality Management Systems (QMS) in manufacturing, fostering continuous process improvement and knowledge management. However, there is no human-centred software architecture focused on QMS that enables the integration of LLM-CAs into manufacturing in the current literature. This study addresses this gap by designing a component-based architecture considering requirement analysis and software development process. Validation was conducted via iterative expert focus groups. The proposed architecture ensures flexibility, scalability, modularity, and work augmentation within QMS. Moreover, it paves the way for its operationalization with industrial partners, showcasing its potential for advancing manufacturing processes.

Human-Centered AI

Human-Centered AI designs and evaluates AI around people's goals, abilities, values, relationships, and social contexts.

See all 169 papers

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory
May 31, 2026Ruiyin Li, Yiran Zhang, Xiyu Zhou +6Software Engineering Software Engineering Agents
School of Computer Science, Wuhan University, Wuhan, China · Nanyang Technological University, Singapore, Singapore
A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing
Aug 7, 2026Fouad Bahrpeyma, Dirk ReicheltManufacturing Decentralized MARL
Smart Production Systems, HTW Dresden, Saxony, Germany
Utilizing LLMs for Industrial Process Automation
Feb 26, 2026Salim FaresIndustrial Automation Automated Software Engineering
University of Passau, Passau, Germany

May 31, 2026J/K move · Enter open · S save

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

Ruiyin Li, Yiran Zhang, Xiyu Zhou, Yangxiao Cai+5

School of Computer Science, Wuhan University, Wuhan, China · Nanyang Technological University, Singapore, Singapore

Software Engineering Software Engineering Agents Multi-Agent Orchestration Software Architecture Design

Open paper AskPDF arXiv

Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes and adapting to evolving requirements. Traditionally, this process has been time-consuming, labor-intensive, and heavily reliant on architects, often resulting in limited exploration of alternative architectural decompositions and styles, especially under the pressures of agile development. While LLM-based agents have shown promising performance across various software engineering tasks, their application to architecture design remains relatively scarce and requires systematic exploration. To address these challenges, we proposed MAAD (Multi-Agent Architecture Design), a knowledge-driven framework that orchestrates four specialized agents (i.e., Analyst, Modeler, Designer and Evaluator) to autonomously and collaboratively transform requirements specifications into comprehensive, multi-view architectural blueprints with quality attribute assessments. MAAD incorporates RAG to inject recognized architectural standards and patterns into the workflow and leverages a hierarchical memory mechanism that captures design history for iterative refinement. We evaluated MAAD through comparative experiments against MetaGPT, using quantitative architecture-level metrics across 10 case studies and qualitative feedback from industry architects on 10 real-world specifications. Results show that MAAD generates more complete, modular, and traceable architectures than the baseline, and its dedicated Evaluator agent autonomously produces structured quality evaluation reports that significantly reduce manual validation efforts. Furthermore, we found that the quality of the generated architecture heavily depends on the underlying LLM's reasoning capacity, with GPT-5.2 and Qwen3.5 outperforming other models across most evaluation settings.

Abstract

Human-Centered AI

Explore similar work

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing

Utilizing LLMs for Industrial Process Automation