{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:40:32Z","timestamp":1771915232158,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":44,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007397","name":"Charles University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007397","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Softw Tools Technol Transfer"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Ensemble-based component systems have been used for many years to develop collective adaptive systems (CAS). The DEECo component model offers a framework for modeling and implementing ensemble-based component systems. Being expressive enough and having semantics specifically tailored towards dynamically evolving systems, DEECo has proven to be fairly powerful in modeling complex and dynamic architectures. We see great potential in employing large language models (LLMs) to simplify creating and refining the DEECo architectures. Since this constitutes a large research scope, in this paper, we focus on initial experiments to demonstrate how well generic LLMs (two OpenAI models executed remotely and four open-source models executed locally) understand the advanced concepts of ensemble-based CAS embodied in DEECo. We do so by systematically asking six questions about specific details of three DEECo applications that differ in the way they are specified. Our results indicate that LLMs can indeed understand ensemble-based architectures and show how this is influenced by the specification means. In particular, using external DSL, which is very self-explanatory, gave good results out of the box. Specifications embedded in existing programming languages needed a prior explanation of how to interpret them.<\/jats:p>","DOI":"10.1007\/s10009-025-00835-9","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T11:30:23Z","timestamp":1768390223000},"page":"641-655","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Understanding ensemble-based component architectures by LLMs"],"prefix":"10.1007","volume":"27","author":[{"given":"Michal","family":"T\u00f6pfer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom\u00e1\u0161","family":"Bure\u0161","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petr","family":"Hn\u011btynka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franti\u0161ek","family":"Pl\u00e1\u0161il","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"835_CR1","series-title":"LNCS","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16310-9","volume-title":"Software Engineering for Collective Autonomic Systems (The ASCENS Approach)","author":"M. Wirsing","year":"2015","unstructured":"Wirsing, M., H\u00f6lzl, M., Koch, N., Mayer, P.: Software Engineering for Collective Autonomic Systems (The ASCENS Approach). LNCS, vol.\u00a08998 (2015). https:\/\/doi.org\/10.1007\/978-3-319-16310-9"},{"key":"835_CR2","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1145\/2465449.2465462","volume-title":"Proceedings of CBSE 2013, Vancouver, Canada","author":"T. Bure\u0161","year":"2013","unstructured":"Bure\u0161, T., Gerostathopoulos, I., Hn\u011btynka, P., Keznikl, J., Kit, M., Pl\u00e1\u0161il, F.: DEECO: an ensemble-based component system. In: Proceedings of CBSE 2013, Vancouver, Canada, pp.\u00a081\u201390 (2013). https:\/\/doi.org\/10.1145\/2465449.2465462"},{"key":"835_CR3","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/SEAMS.2017.17","volume-title":"Proceedings of SEAMS 2017, Buenos Aires, Argentina","author":"F. Krijt","year":"2017","unstructured":"Krijt, F., Jir\u00e1\u010dek, Z., Bure\u0161, T., Hn\u011btynka, P., Gerostathopoulos, I.: Intelligent ensembles - a declarative group description language and Java framework. In: Proceedings of SEAMS 2017, Buenos Aires, Argentina, pp.\u00a0116\u2013122 (2017). https:\/\/doi.org\/10.1109\/SEAMS.2017.17"},{"key":"835_CR4","series-title":"LNCS","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03424-5_12","volume-title":"Proceedings of ISoLA 2018, Limassol, Cyprus","author":"R. Al Ali","year":"2018","unstructured":"Al Ali, R., Bure\u0161, T., Hn\u011btynka, P., Krijt, F., Pl\u00e1\u0161il, F., Vin\u00e1rek, J.: Dynamic security specification through autonomic component ensemble. In: Proceedings of ISoLA 2018, Limassol, Cyprus. LNCS, vol.\u00a011246 (2018). https:\/\/doi.org\/10.1007\/978-3-030-03424-5_12"},{"key":"835_CR5","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/ACSOSC56246.2022.00033","volume-title":"Companion Proceedings of ACSOS 2022, Virtual Event","author":"M. T\u00f6pfer","year":"2022","unstructured":"T\u00f6pfer, M., Abdullah, M., Kruli\u0161, M., Bure\u0161, T., Hn\u011btynka, P.: ML-DEECo: a machine-learning-enabled framework for self-organizing components. In: Companion Proceedings of ACSOS 2022, Virtual Event, pp.\u00a066\u201369 (2022). https:\/\/doi.org\/10.1109\/ACSOSC56246.2022.00033"},{"key":"835_CR6","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-031-75107-3_13","volume-title":"Proceedings of ISOLA 2024, Crete, Greece","author":"M. T\u00f6pfer","year":"2024","unstructured":"T\u00f6pfer, M., Khalyeyev, D., Bure\u0161, T., Hn\u011btynka, P., Pl\u00e1\u0161il, F.: How well do LLMs understand DEECo ensemble-based component architectures. In: Proceedings of ISOLA 2024, Crete, Greece, pp.\u00a0208\u2013223 (2024). https:\/\/doi.org\/10.1007\/978-3-031-75107-3_13"},{"issue":"4","key":"835_CR7","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1145\/1118890.1118892","volume":"37","author":"M. Mernik","year":"2005","unstructured":"Mernik, M., Heering, J., Sloane, A.M.: When and how to develop domain-specific languages. ACM Comput. Surv. 37(4), 316\u2013344 (2005). https:\/\/doi.org\/10.1145\/1118890.1118892","journal-title":"ACM Comput. Surv."},{"issue":"4","key":"835_CR8","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s10009-020-00556-1","volume":"22","author":"R. Al Ali","year":"2020","unstructured":"Al Ali, R., Bure\u0161, T., Hn\u011btynka, P., Mat\u011bjek, J., Pl\u00e1\u0161il, F., Vin\u00e1rek, J.: Toward autonomically composable and context-dependent access control specification through ensembles. Int. J. Softw. Tools Technol. Transf. 22(4), 511\u2013522 (2020). https:\/\/doi.org\/10.1007\/s10009-020-00556-1","journal-title":"Int. J. Softw. Tools Technol. Transf."},{"key":"835_CR9","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1145\/3387939.3391599","volume-title":"Proceedings of SEAMS 2020, Seoul, Korea","author":"P. Hn\u011btynka","year":"2020","unstructured":"Hn\u011btynka, P., Bure\u0161, T., Gerostathopoulos, I., Pacovsk\u00fd, J.: Using component ensembles for modeling autonomic component collaboration in smart farming. In: Proceedings of SEAMS 2020, Seoul, Korea, pp.\u00a0156\u2013162 (2020). https:\/\/doi.org\/10.1145\/3387939.3391599"},{"key":"835_CR10","volume-title":"Lost in the Middle: How Language Models Use Long Contexts","author":"N.F. Liu","year":"2023","unstructured":"Liu, N.F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., Liang, P.: Lost in the Middle: How Language Models Use Long Contexts (2023). https:\/\/arxiv.org\/abs\/2307.03172"},{"key":"835_CR11","first-page":"1877","volume-title":"Proceedings NIPS 2020, Vancouver, Canada","author":"T.B. Brown","year":"2020","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D.M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., Amodei, D.: Language models are few-shot learners. In: Proceedings NIPS 2020, Vancouver, Canada, pp.\u00a01877\u20131901 (2020)"},{"key":"835_CR12","doi-asserted-by":"publisher","unstructured":"Chen, Q., Qin, L., Liu, J., Peng, D., Guan, J., Wang, P., Hu, M., Zhou, Y., Gao, T., Che, W.: Towards Reasoning Era: a Survey of Long Chain-of-Thought for Reasoning Large Language Models (2025). arXiv:2503.09567 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2503.09567","DOI":"10.48550\/arXiv.2503.09567"},{"key":"835_CR13","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/WICSA-ECSA.212.39","volume-title":"Proceedings of WICSA\/ECSA 2012, Helsinki, Finland","author":"J. Keznikl","year":"2012","unstructured":"Keznikl, J., Bure\u0161, T., Pl\u00e1\u0161il, F., Kit, M.: Towards dependable emergent ensembles of components: the DEECo component model. In: Proceedings of WICSA\/ECSA 2012, Helsinki, Finland, pp.\u00a0249\u2013252 (2012). https:\/\/doi.org\/10.1109\/WICSA-ECSA.212.39"},{"key":"835_CR14","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1613\/jair.614","volume":"11","author":"D. Opitz","year":"1999","unstructured":"Opitz, D., Maclin, R.: Popular ensemble methods: an empirical study. J. Artif. Intell. Res. 11, 169\u2013198 (1999). https:\/\/doi.org\/10.1613\/jair.614","journal-title":"J. Artif. Intell. Res."},{"issue":"2","key":"835_CR15","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10664-008-9102-8","volume":"14","author":"P. Runeson","year":"2008","unstructured":"Runeson, P., H\u00f6st, M.: Guidelines for conducting and reporting case study research in software engineering. Empir. Softw. Eng. 14(2), 131\u2013164 (2008). https:\/\/doi.org\/10.1007\/s10664-008-9102-8","journal-title":"Empir. Softw. Eng."},{"key":"835_CR16","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2009.03300","volume-title":"Measuring Massive Multitask Language Understanding","author":"D. Hendrycks","year":"2021","unstructured":"Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., Steinhardt, J.: Measuring Massive Multitask Language Understanding (2021). https:\/\/doi.org\/10.48550\/arxiv.2009.03300"},{"key":"835_CR17","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1803.05457","volume-title":"Think You Have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","author":"P. Clark","year":"2018","unstructured":"Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., Tafjord, O.: Think You Have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge (2018). https:\/\/doi.org\/10.48550\/arxiv.1803.05457"},{"key":"835_CR18","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1907.10641","volume-title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","author":"K. Sakaguchi","year":"2019","unstructured":"Sakaguchi, K., Bras, R.L., Bhagavatula, C., Choi, Y.: WinoGrande: An Adversarial Winograd Schema Challenge at Scale (2019). https:\/\/doi.org\/10.48550\/arxiv.1907.10641"},{"key":"835_CR19","doi-asserted-by":"publisher","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: HellaSwag: Can a Machine Really Finish Your Sentence? (2019). https:\/\/doi.org\/10.48550\/arxiv.1905.07830","DOI":"10.48550\/arxiv.1905.07830"},{"key":"835_CR20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.14168","volume-title":"Training Verifiers to Solve Math Word Problems","author":"K. Cobbe","year":"2021","unstructured":"Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., Hesse, C., Schulman, J.: Training Verifiers to Solve Math Word Problems (2021). https:\/\/doi.org\/10.48550\/arXiv.2110.14168"},{"key":"835_CR21","doi-asserted-by":"publisher","unstructured":"Sutawika, L., Schoelkopf, H., Gao, L., Abbasi, B., Biderman, S., Tow, J., fattori, Lovering, C., farzanehnakhaee70, Phang, J., Thite, A., Fazz, Wang, T., Muennighoff, N., Aflah, sdtblck, nopperl, gakada, tttyuntian, researcher2, Chris, Etxaniz, J., Lee, H.A., Kasner, Z., Khalid, Hsu, J., Kanekar, A., Ammanamanchi, P.S., Boykis, V., AndyZwei: EleutherAI\/lm-evaluation-harness: v0.4.2. Zenodo (2024). https:\/\/doi.org\/10.5281\/zenodo.10829972","DOI":"10.5281\/zenodo.10829972"},{"key":"835_CR22","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2211.09110","volume-title":"Holistic Evaluation of Language Models","author":"P. Liang","year":"2023","unstructured":"Liang, P., Bommasani, R., Lee, T., Tsipras, D., Soylu, D., Yasunaga, M., Zhang, Y., Narayanan, D., Wu, Y., Kumar, A., Newman, B., Yuan, B., Yan, B., Zhang, C., Cosgrove, C., Manning, C.D., R\u00e9, C., Acosta-Navas, D., Hudson, D.A., Zelikman, E., Durmus, E., Ladhak, F., Rong, F., Ren, H., Yao, H., Wang, J., Santhanam, K., Orr, L., Zheng, L., Yuksekgonul, M., Suzgun, M., Kim, N., Guha, N., Chatterji, N., Khattab, O., Henderson, P., Huang, Q., Chi, R., Xie, S.M., Santurkar, S., Ganguli, S., Hashimoto, T., Icard, T., Zhang, T., Chaudhary, V., Wang, W., Li, X., Mai, Y., Zhang, Y., Koreeda, Y.: Holistic Evaluation of Language Models (2023). https:\/\/doi.org\/10.48550\/arxiv.2211.09110"},{"key":"835_CR23","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.5196419","volume-title":"Generative AI for Software Architecture. Applications, Trends, Challenges, and Future Directions","author":"M. Esposito","year":"2025","unstructured":"Esposito, M., Li, X., Moreschini, S., Ahmad, N., Cerny, T., Vaidhyanathan, K., Lenarduzzi, V., Taibi, D.: Generative AI for Software Architecture. Applications, Trends, Challenges, and Future Directions (2025). https:\/\/arxiv.org\/abs\/2503.13310"},{"key":"835_CR24","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1109\/icsa-c63560.2024.00059","volume-title":"Companion Proc. of ICSA 2024, Hyderabad, India","author":"J. Jahi\u0107","year":"2024","unstructured":"Jahi\u0107, J., Sami, A.: State of practice: LLMs in software engineering and software architecture. In: Companion Proc. of ICSA 2024, Hyderabad, India, pp.\u00a0311\u2013318 (2024). https:\/\/doi.org\/10.1109\/icsa-c63560.2024.00059"},{"key":"835_CR25","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2403.08604","volume-title":"DevBench: A Comprehensive Benchmark for Software Development","author":"B. Li","year":"2024","unstructured":"Li, B., Wu, W., Tang, Z., Shi, L., Yang, J., Li, J., Yao, S., Qian, C., Hui, B., Zhang, Q., Yu, Z., Du, H., Yang, P., Lin, D., Peng, C., Chen, K.: DevBench: A Comprehensive Benchmark for Software Development (2024). https:\/\/doi.org\/10.48550\/arxiv.2403.08604"},{"key":"835_CR26","doi-asserted-by":"publisher","unstructured":"Dhar, R., Vaidhyanathan, K., Varma, V.: Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study. (Accepted to ICSA 2024) (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.01709","DOI":"10.48550\/arXiv.2403.01709"},{"key":"835_CR27","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1145\/3593434.3593468","volume-title":"Proceedings of EASE 2023, Oulu, Finland","author":"A. Ahmad","year":"2023","unstructured":"Ahmad, A., Waseem, M., Liang, P., Fahmideh, M., Aktar, M.S., Mikkonen, T.: Towards human-bot collaborative software architecting with ChatGPT. In: Proceedings of EASE 2023, Oulu, Finland, pp.\u00a0279\u2013285 (2023). https:\/\/doi.org\/10.1145\/3593434.3593468"},{"key":"835_CR28","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1145\/3643915.3644088","volume-title":"Proc. of SEAMS 2024, Lisbon, Portugal","author":"J. Li","year":"2024","unstructured":"Li, J., Zhang, M., Li, N., Weyns, D., Jin, Z., Tei, K.: Exploring the potential of large language models in self-adaptive systems. In: Proc. of SEAMS 2024, Lisbon, Portugal, pp.\u00a077\u201383 (2024). https:\/\/doi.org\/10.1145\/3643915.3644088"},{"key":"835_CR29","doi-asserted-by":"publisher","DOI":"10.1145\/3686803","author":"J. Li","year":"2024","unstructured":"Li, J., Zhang, M., Li, N., Weyns, D., Jin, Z., Tei, K.: Generative ai for self-adaptive systems: state of the art and research roadmap. ACM Trans. Auton. Adapt. Syst. 19(3) (2024). https:\/\/doi.org\/10.1145\/3686803","journal-title":"ACM Trans. Auton. Adapt. Syst."},{"key":"835_CR30","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2404.09866","volume-title":"Reimagining Self-Adaptation in the Age of Large Language Models","author":"R. Donakanti","year":"2024","unstructured":"Donakanti, R., Jain, P., Kulkarni, S., Vaidhyanathan, K.: Reimagining Self-Adaptation in the Age of Large Language Models (2024). https:\/\/doi.org\/10.48550\/arxiv.2404.09866"}],"container-title":["International Journal on Software Tools for Technology Transfer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10009-025-00835-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10009-025-00835-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10009-025-00835-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T16:13:06Z","timestamp":1771863186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10009-025-00835-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":30,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["835"],"URL":"https:\/\/doi.org\/10.1007\/s10009-025-00835-9","relation":{},"ISSN":["1433-2779","1433-2787"],"issn-type":[{"value":"1433-2779","type":"print"},{"value":"1433-2787","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"13 December 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2026","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}