{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T17:06:22Z","timestamp":1780506382649,"version":"3.54.1"},"reference-count":51,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Federal Ministry of Economic Affairs and Energy","award":["FKZ: 19S24001I"],"award-info":[{"award-number":["FKZ: 19S24001I"]}]},{"name":"RWTH Aachen University Open Access Publication Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>The complexity of modern cyber\u2013physical systems is steadily increasing as their functional scope expands and as regulations become more demanding. To cope with this complexity, organizations are adopting methodologies such as model-based systems engineering (MBSE). By creating system models, MBSE promises significant advantages such as improved traceability, consistency, and collaboration. On the other hand, the adoption of MBSE faces challenges in both the introduction and the operational use. In the introduction phase, challenges include high initial effort and steep learning curves. In the operational use phase, challenges arise from the difficulty of retrieving and reusing information stored in system models. Research on the support of MBSE through artificial intelligence (AI), especially generative AI, has so far focused mainly on easing the introduction phase, for example by using large language models (LLMs) to assist in creating system models. However, generative AI could also support the operational use phase by helping stakeholders access the information embedded in existing system models. This study introduces an LLM-based multi-agent system that applies a Graph Retrieval-Augmented Generation (GraphRAG) strategy to access and utilize information stored in MBSE system models. The system\u2019s capabilities are demonstrated through a chatbot that answers questions about the underlying system model. This solution reduces the complexity and effort involved in retrieving system model information and improves accessibility for stakeholders who lack advanced knowledge in MBSE methodologies. The chatbot was evaluated using the architecture of a battery electric vehicle as a reference model and a set of 100 curated questions and answers. When tested across four large language models, the best-performing model achieved an accuracy of 93 percent in providing correct answers.<\/jats:p>","DOI":"10.3390\/systems14010083","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T10:25:23Z","timestamp":1768213523000},"page":"83","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enabling Humans and AI Systems to Retrieve Information from System Architectures in Model-Based Systems Engineering"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1607-6838","authenticated-orcid":false,"given":"Vincent","family":"Quast","sequence":"first","affiliation":[{"name":"Institute of Machine Elements and Systems Engineering, RWTH Aachen University, 52062 Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7564-288X","authenticated-orcid":false,"given":"Georg","family":"Jacobs","sequence":"additional","affiliation":[{"name":"Institute of Machine Elements and Systems Engineering, RWTH Aachen University, 52062 Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7049-151X","authenticated-orcid":false,"given":"Simon","family":"Dehn","sequence":"additional","affiliation":[{"name":"Institute of Machine Elements and Systems Engineering, RWTH Aachen University, 52062 Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4451-3978","authenticated-orcid":false,"given":"Gregor","family":"H\u00f6pfner","sequence":"additional","affiliation":[{"name":"Institute of Machine Elements and Systems Engineering, RWTH Aachen University, 52062 Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref_1","unstructured":"Salado, A. (2024). Introduction to Systems Engineering in the 21st Century: Volume 1. Systems Engineering Series, Cuadernos de Isdefe."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Griffor, E.R., Greer, C., Wollman, D.A., and Burns, M.J. (2017). Framework for Cyber-Physical Systems: Volume 1, Overview.","DOI":"10.6028\/NIST.SP.1500-201"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1002\/sys.21438","article-title":"Model-based systems engineering: Motivation, current status, and research opportunities","volume":"21","author":"Madni","year":"2018","journal-title":"Syst. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1002\/sys.21566","article-title":"Value and benefits of model-based systems engineering (MBSE): Evidence from the literature","volume":"24","author":"Henderson","year":"2021","journal-title":"Syst. Eng."},{"key":"ref_5","unstructured":"Chami, M., and Bruel, J.-M. (2018, January 8). A Survey on MBSE Adoption Challenges. Proceedings of the INCOSE EMEA Sector Systems Engineering Conference (INCOSE EMEASEC 2018), Berlin, Germany. Available online: https:\/\/hal.science\/hal-02124402v1\/document."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1017\/pds.2025.10267","article-title":"Navigating viewpoints in MBSE: Challenges, potential and pathways for stakeholder participation in industry","volume":"5","author":"Koldewey","year":"2025","journal-title":"Proc. Des. Soc."},{"key":"ref_7","first-page":"96","article-title":"AI-Augmented Model-Based Systems Engineering","volume":"120","author":"Bernijazov","year":"2025","journal-title":"Z. F\u00fcr Wirtsch. Fabr."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2542","DOI":"10.1002\/iis2.13285","article-title":"LLM-based Approach to Automatically Establish Traceability between Requirements and MBSE","volume":"34","author":"Bonner","year":"2024","journal-title":"INCOSE Int. Symp."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2168","DOI":"10.1002\/iis2.13262","article-title":"Leveraging Large Language Models for Direct Interaction with SysML v2","volume":"34","author":"DeHart","year":"2024","journal-title":"INCOSE Int. Symp."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1002\/iis2.13212","article-title":"Integrating AI with MBSE for Data Extraction from Medical Standards","volume":"34","author":"Ghanawi","year":"2024","journal-title":"INCOSE Int. Symp."},{"key":"ref_11","unstructured":"Elias, B., Jounes, A.C., Katharina, P., Markus, M.P., and Christian, N. (2026, January 08). Integrating SysML v2 into a GRAG LLM Pipeline: Design, Implementation and Evaluation. Available online: https:\/\/www.researchgate.net\/publication\/395749011_Integrating_SysML_v2_into_a_GRAG_LLM_Pipeline_Design_Implementation_and_Evaluation."},{"key":"ref_12","unstructured":"INCOSE (2025, August 26). MBSE-Initiative. Available online: https:\/\/www.incose.org\/communities\/working-groups-initiatives\/mbse-initiative."},{"key":"ref_13","unstructured":"OMG (2025, November 18). SysML v2: The Next Generation Systems Modeling Language. Available online: https:\/\/www.omg.org\/sysml\/sysmlv2\/."},{"key":"ref_14","first-page":"1","article-title":"Survey of model-based systems engineering (MBSE) methodologies","volume":"25","author":"Estefan","year":"2007","journal-title":"Incose MBSE Focus Group"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1002\/j.2334-5837.2015.00078.x","article-title":"Implementing the MBSE Cultural Change: Organization, Coaching and Lessons Learned","volume":"25","author":"Bonnet","year":"2015","journal-title":"INCOSE Int. Symp."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bayer, T., Day, J., Dodd, E., Jones-Wilson, L., Rivera, A., Shougarian, N., Susca, S., and Wagner, D. (2021, January 6\u201313). Europa Clipper: MBSE Proving Ground. Proceedings of the 2021 IEEE Aerospace Conference (50100), Big Sky, MT, USA.","DOI":"10.1109\/AERO50100.2021.9438186"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1002\/iis2.13157","article-title":"The Effects of the Assessed Perceptions of MBSE on Adoption","volume":"34","author":"Call","year":"2024","journal-title":"INCOSE Int. Symp."},{"key":"ref_18","unstructured":"Bell, R., Longshore, R., and Madachy, R. (2024). Introducing SysEngBench: A Novel Benchmark for Assessing Large Language Models in Systems Engineering, Acquisition Research Program. Available online: https:\/\/dair.nps.edu\/handle\/123456789\/5135."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1002\/iis2.13201","article-title":"AI Systems Modeling Enhancer (AI-SME): Initial Investigations into a ChatGPT-enabled MBSE Modeling Assistant","volume":"34","author":"Johns","year":"2024","journal-title":"INCOSE Int. Symp."},{"key":"ref_20","unstructured":"Chami, M., Zoghbi, C., and Bruel, J.-M. (2019). A First Step towards AI for MBSE: Generating a Part of SysML Models from Text Using AI. INCOSE Artificial Intelligence: 2019 Conference Proceedings, Independently published. [1st ed.]. Available online: https:\/\/www.researchgate.net\/publication\/337338933_A_First_Step_towards_AI_for_MBSE_Generating_a_Part_of_SysML_Models_from_Text_Using_AI."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1017\/pds.2025.10050","article-title":"Advancing systems engineering with artificial intelligence: A review on the future potential challenges and pathways","volume":"5","author":"Poulsen","year":"2025","journal-title":"Proc. Des. Soc."},{"key":"ref_22","unstructured":"Manno, N. (2026, January 08). Accelerating Semantic Digital Thread User Queries Using LLMs 2024. Available online: https:\/\/sercuarc.org\/wp-content\/uploads\/2025\/06\/Slides-Accelerating-Semantic-Digital-Thread-User-Queries-Using-LLMs.pdf."},{"key":"ref_23","unstructured":"Pennock, M., Ponnock, J., Bannon, T., and Dahmann, J. (2026, January 08). AI-Enabled Mission Engineering. Available online: https:\/\/sercuarc.org\/wp-content\/uploads\/2025\/09\/Pennock_AI_Enabled_ME.pdf."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Caldarini, G., Jaf, S., and McGarry, K. (2022). A Literature Survey of Recent Advances in Chatbots. Information, 13.","DOI":"10.3390\/info13010041"},{"key":"ref_25","unstructured":"Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., and Lin, H. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_26","unstructured":"Sharma, C. (2025). Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers. arXiv."},{"key":"ref_27","unstructured":"Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., Metropolitansky, D., Ness, R.O., and Larson, J. (2026, January 08). From Local to Global: A Graph RAG Approach to Query-Focused Summarization. Available online: http:\/\/arxiv.org\/pdf\/2404.16130v2."},{"key":"ref_28","unstructured":"Han, H., Ma, L., Shomer, H., Wang, Y., Lei, Y., Guo, K., Hua, Z., Long, B., Liu, H., and Aggarwal, C.C. (2025). RAG vs. GraphRAG: A Systematic Evaluation and Key Insights. arXiv."},{"key":"ref_29","unstructured":"Peng, B., Zhu, Y., Liu, Y., Bo, X., Shi, H., Hong, C., Zhang, Y., and Tang, S. (2026, January 08). Graph Retrieval-Augmented Generation: A Survey. Available online: http:\/\/arxiv.org\/pdf\/2408.08921v2."},{"key":"ref_30","unstructured":"Jiang, X., Zhang, R., Xu, Y., Qiu, R., Fang, Y., Wang, Z., Tang, J., Ding, H., Chu, X., and Zhao, J. (2023). HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Li, S., Gao, Y., Jiang, H., Yin, Q., Li, Z., Yan, X., Zhang, C., and Yin, B. (2023). Graph Reasoning for Question Answering with Triplet Retrieval. arXiv.","DOI":"10.18653\/v1\/2023.findings-acl.208"},{"key":"ref_32","first-page":"132876","article-title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","volume":"37","author":"He","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hu, Y., Lei, Z., Zhang, Z., Pan, B., Ling, C., and Zhao, L. (2024). GRAG: Graph Retrieval-Augmented Generation. arXiv.","DOI":"10.18653\/v1\/2025.findings-naacl.232"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sarmah, B., Hall, B., Rao, R., Patel, S., Pasquali, S., and Mehta, D. (2024). HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction. arXiv.","DOI":"10.1145\/3677052.3698671"},{"key":"ref_35","unstructured":"Delile, J., Mukherjee, S., van Pamel, A., and Zhukov, L. (2024). Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhou, K., Dong, Z., Ye, K., Zhao, W.X., and Wen, J.-R. (2023). StructGPT: A General Framework for Large Language Model to Reason over Structured Data. arXiv.","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Mavromatis, C., and Karypis, G. (2024). GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning. arXiv.","DOI":"10.18653\/v1\/2025.findings-acl.856"},{"key":"ref_38","first-page":"59532","article-title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","volume":"37","author":"Shu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sun, H., Bedrax-Weiss, T., and Cohen, W.W. (2019). PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text, Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1242"},{"key":"ref_40","unstructured":"Jiang, J., Zhou, K., Zhao, W.X., Song, Y., Zhu, C., Zhu, H., and Wen, J.-R. (2024). KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph, Association for Computational Linguistics."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Jin, B., Xie, C., Zhang, J., Roy, K.K., Zhang, Y., Li, Z., Li, R., Tang, X., Wang, S., and Meng, Y. (2024). Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.11"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Sun, L., Tao, Z., Li, Y., and Arakawa, H. (2024). ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.442"},{"key":"ref_43","unstructured":"Wang, X., Yang, Q., Qiu, Y., Liang, J., He, Q., Gu, Z., Xiao, Y., and Wang, W. (2023). KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases. arXiv."},{"key":"ref_44","unstructured":"Munikoti, S., Acharya, A., Wagle, S., and Horawalavithana, S. (2023). ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science. arXiv."},{"key":"ref_45","unstructured":"Li, Z., Guo, Q., Shao, J., Song, L., Bian, J., Zhang, J., and Wang, R. (2024). Graph Neural Network Enhanced Retrieval for Question Answering of LLMs. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Yang, R., Liu, H., Marrese-Taylor, E., Zeng, Q., Ke, Y.H., Li, W., Cheng, L., Chen, Q., Caverlee, J., and Matsuo, Y. (2024). KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques. arXiv.","DOI":"10.18653\/v1\/2024.bionlp-1.13"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Peng, Z., and Yang, Y. (2024). Connecting the Dots: Inferring Patent Phrase Similarity with Retrieved Phrase Graphs. arXiv.","DOI":"10.18653\/v1\/2024.findings-naacl.121"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"e8","DOI":"10.1017\/dce.2020.7","article-title":"Machine learning approaches to identify and design low thermal conductivity oxides for thermoelectric applications","volume":"1","author":"Tewari","year":"2020","journal-title":"Data Centric Eng."},{"key":"ref_49","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2022). ReAct: Synergizing Reasoning and Acting in Language Models. arXiv."},{"key":"ref_50","unstructured":"together.ai (2025, November 17). Llama 3.3 70B API. Available online: https:\/\/www.together.ai\/models\/llama-3-3-70b."},{"key":"ref_51","unstructured":"(2025, November 17). Googel AI Studio. Available online: https:\/\/aistudio.google.com\/."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/83\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T11:20:10Z","timestamp":1768216810000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/83"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["systems14010083"],"URL":"https:\/\/doi.org\/10.3390\/systems14010083","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]}}}