Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems
cs.AI, cs.CL, cs.SY, eess.SY
Submitted: 2026-01-30
Updated: 2026-09-22
Comments: 27 pages, 10 figures
Code: https://github.com/bankh/xLM_DSM
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: We explore the potential of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Graph-based RAG (GraphRAG) for generating Design Structure Matrices (DSMs).
Terminology
Abstract
We explore the potential of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Graph-based RAG (GraphRAG) for generating Design Structure Matrices (DSMs). We test these methods on two distinct use cases--a power screwdriver and a CubeSat with known architectural references--evaluating their performance on two key tasks: determining relationships between predefined components, and the more complex challenge of identifying components and their subsequent relationships. We measure the performance by assessing each element of the DSM and overall architecture. Despite design and computational challenges, we identify opportunities for automated DSM generation, with all code publicly available for reproducibility and further feedback from the domain experts.
Sources
- An Approach for System Analysis with MBSE and Graph Data Engineering
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-V3 Technical Report
- GPT-4 Technical Report
- The Llama 3 Herd of Models
- Scaling Laws for Neural Language Models
- Language Models are Few-Shot Learners
- Augmenting LLMs with Knowledge: A survey on hallucination prevention
- When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
- Generalization through Memorization: Nearest Neighbor Language Models
- Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
- Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
- Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering
- Exploring the Capabilities of Large Language Models for Generating Diverse Design Solutions
- DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems