{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T03:40:46Z","timestamp":1783741246007,"version":"3.55.0"},"reference-count":34,"publisher":"Maximum Academic Press","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"unspecified","delay-in-days":352,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["The Knowledge Engineering Review"],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Motivated by the astonishing capabilities of large language models (LLMs) in text-generation, reasoning, and simulation of complex human behaviors, in this paper, we propose a novel multi-component LLM-based framework, namely LLM4ACOE, that fully automates the collaborative ontology engineering (COE) process using role-playing simulation of LLM agents and retrieval augmented generation (RAG) technology. The proposed solution enhances the LLM-powered role-playing simulation with RAG \u2018feeding\u2019 the LLM with three different types of external knowledge. This knowledge corresponds to the knowledge required by each of the COE roles (agents), using a component-based framework, as follows: (a) domain-specific data-centric documents, (b) OWL documentation, and (c) ReAct guidelines. The aforementioned components are evaluated in combination, with the aim of investigating their impact on the quality of generated ontologies. The aim of this work is twofold, (a) to identify the capacity of LLM-based agents to generate acceptable (by human-experts) ontologies through agentic collaborative ontology engineering (ACOE) role-playing simulation, at specific levels of acceptance (accuracy, validity, and expressiveness of ontologies) without human intervention and (b) to investigate whether and\/or to what extent the selected RAG components affect the quality of the generated ontologies. The evaluation of this novel approach is performed using ChatGPT-o in the domain of search and rescue (SAR) missions. To assess the generated ontologies, quantitative and qualitative measures are employed, focusing on coverage, expressiveness, structure, and human involvement.<\/jats:p>","DOI":"10.1017\/s026988892510009x","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:31:57Z","timestamp":1766133117000},"update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":4,"title":["Automating agentic collaborative ontology engineering with role-playing simulation of LLM-powered agents and RAG technology"],"prefix":"10.48130","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9769-5583","authenticated-orcid":false,"given":"Andreas","family":"Soularidis","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03zsp3p94","id-type":"ROR","asserted-by":"publisher"}],"name":"University of the Aegean, University Hill"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Doumanas","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03zsp3p94","id-type":"ROR","asserted-by":"publisher"}],"name":"University of the Aegean, University Hill"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7838-9691","authenticated-orcid":false,"given":"Konstantinos","family":"Kotis","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03zsp3p94","id-type":"ROR","asserted-by":"publisher"}],"name":"University of the Aegean, University Hill"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George A.","family":"Vouros","sequence":"additional","affiliation":[{"name":"University of Piraeus"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"27968","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"S026988892510009X_ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63223-5_27"},{"key":"S026988892510009X_ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.11484"},{"key":"S026988892510009X_ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.05374"},{"key":"S026988892510009X_ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78952-6_4"},{"key":"S026988892510009X_ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00181"},{"key":"S026988892510009X_ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.06899"},{"key":"S026988892510009X_ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.08820"},{"key":"S026988892510009X_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MIPRO60963.2024.10569238"},{"key":"S026988892510009X_ref26","doi-asserted-by":"publisher","DOI":"10.4018\/ijswis.2014040102"},{"key":"S026988892510009X_ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3549737.3549765"},{"key":"S026988892510009X_ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06647-8"},{"key":"S026988892510009X_ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615220"},{"key":"S026988892510009X_ref31","unstructured":"Updyke, D. , Podnar, T. & Huff, S. 2023. Simulating realistic human activity using large language model directives."},{"key":"S026988892510009X_ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.15524"},{"key":"S026988892510009X_ref17","unstructured":"Litaina, T. , Soularidis, A. , Bouchouras, G. , Kotis, K. & Kavakli, E. 2024. Towards llm-based semantic analysis of historical legal documents. In SemDH@ESWC. https:\/\/ceur-ws.org\/Vol-3724\/short2.pdf"},{"key":"S026988892510009X_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SYNASC61333.2023.00038"},{"key":"S026988892510009X_ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.23584"},{"key":"S026988892510009X_ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"S026988892510009X_ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC59802.2024.00050"},{"key":"S026988892510009X_ref6","doi-asserted-by":"publisher","DOI":"10.1177\/15705838241305067"},{"key":"S026988892510009X_ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PIC53636.2021.9687030"},{"key":"S026988892510009X_ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.399"},{"key":"S026988892510009X_ref30","doi-asserted-by":"crossref","unstructured":"Soularidis, A. , Kotis, K. , Lamolle, M. , Mejdoul, Z. , Lortal, G. & Vouros, G. 2024. Llm-assisted generation of swrl rules from natural language. In 2024 International Conference on AI x Data and Knowledge Engineering (AIxDKE), 7\u201312.","DOI":"10.1109\/AIxDKE63520.2024.00008"},{"key":"S026988892510009X_ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.08345"},{"key":"S026988892510009X_ref32","unstructured":"Yao, S. , Zhao, J. , Yu, D. , Du, N. , Shafran, I. , Narasimhan, K. R. & Cao, Y. 2023. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=WE_vluYUL-X"},{"key":"S026988892510009X_ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10817-014-9305-1"},{"key":"S026988892510009X_ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3670865.3673513"},{"key":"S026988892510009X_ref5","first-page":"1","article-title":"Integrating ontologies and large language models to implement retrieval augmented generation (rag)","volume":"1","author":"DeBellis","year":"2024","journal-title":"Applied Ontology"},{"key":"S026988892510009X_ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-005-0227-4"},{"key":"S026988892510009X_ref27","doi-asserted-by":"crossref","unstructured":"Reddy, G. P. , Pavan Kumar, Y. V. & Prakash, K. P. 2024. Hallucinations in large language models (llms). In 2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), 1\u20136.","DOI":"10.1109\/eStream61684.2024.10542617"},{"key":"S026988892510009X_ref15","doi-asserted-by":"crossref","unstructured":"Kosinski, M. 2024. Evaluating large language models in theory of mind tasks. Proceedings of the National Academy of Sciences 121(45), e2405460121.","DOI":"10.1073\/pnas.2405460121"},{"key":"S026988892510009X_ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.05921"},{"key":"S026988892510009X_ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.14191"},{"key":"S026988892510009X_ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.453"}],"container-title":["The Knowledge Engineering Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S026988892510009X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T14:42:25Z","timestamp":1767624145000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S026988892510009X\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"alternative-id":["S026988892510009X"],"URL":"https:\/\/doi.org\/10.1017\/s026988892510009x","relation":{},"ISSN":["0269-8889","1469-8005"],"issn-type":[{"value":"0269-8889","type":"print"},{"value":"1469-8005","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"\u00a9 The Author(s), 2025. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike licence (https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the same Creative Commons licence is used to distribute the re-used or adapted article and the original article is properly cited. The written permission of Cambridge University Press or the rights holder(s) must be obtained prior to any commercial use.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"e10"}}