{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T14:43:05Z","timestamp":1791470585337,"version":"4.3.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004593","name":"Universidad Aut\u00f3noma de Madrid","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004593","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Softw Eng"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Generative artificial intelligence (AI) is boosting the use of LLM-based conversational assistants in many domains. In software engineering, numerous integrated development environments (IDEs) offer conversational assistants to improve productivity, leading to AI-IDEs. However, the integration of assistants into IDEs is often ad-hoc, rigid and opaque. Moreover, the assistant-generated code is frequently untraceable, and developers struggle to trust it. Given the diversity of software construction processes, AI-IDE architectures should be: (i)\n                    <jats:italic>open<\/jats:italic>\n                    , permitting the on-demand configuration of assistive tasks, and enabling the coordination of assistants potentially built atop diverse LLMs; (ii)\n                    <jats:italic>accountable<\/jats:italic>\n                    , tracing the assistant contributions and exploiting this information to obtain project insights; (iii)\n                    <jats:italic>trustworthy<\/jats:italic>\n                    , allowing the customisation of safeguard protocols for the assistive tasks. To fill this gap, we propose an open, extensible, accountable architecture for AI-IDEs, which incorporates validation loops for trustworthy assistance. We have implemented this architecture as an extensible plugin for Java development within Eclipse, called\n                    <jats:sc>Caret<\/jats:sc>\n                    . We have conducted offline evaluations and a user study, which demonstrate that\n                    <jats:sc>Caret<\/jats:sc>\n                    can be easily extended with new tasks, and its handling of context and validation loops results in effectiveness improvements up to 147.34% compared to the baseline. Overall, our architecture facilitates the seamless integration of LLM-based conversational assistants into IDEs, coping with new assistive demands for specific needs, offering detailed accountability of development contributions, and incorporating configurable validation loops for trustworthy development.\n                  <\/jats:p>","DOI":"10.1007\/s10515-026-00608-x","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:53:34Z","timestamp":1773726814000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Architecting open, accountable, and trustworthy AI-IDEs"],"prefix":"10.1007","volume":"33","author":[{"given":"Albert","family":"Contreras","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esther","family":"Guerra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"de Lara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"608_CR1","unstructured":"Anthropic.: Model context protocol (2025). https:\/\/modelcontextprotocol.io\/introduction"},{"issue":"3","key":"608_CR2","first-page":"114","volume":"4","author":"A Bangor","year":"2009","unstructured":"Bangor, A.: Determining what individual SUS scores mean: Adding an adjective rating scale. J. User Exper. 4(3), 114\u2013123 (2009)","journal-title":"J. User Exper."},{"key":"608_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2025.107751","volume":"183","author":"L Banh","year":"2025","unstructured":"Banh, L., Holldack, F., Strobel, G.: Copiloting the future: How generative AI transforms software engineering. Inf. Softw. Technol. 183, 107751 (2025)","journal-title":"Inf. Softw. Technol."},{"key":"608_CR4","first-page":"29","volume":"8","author":"J Brooke","year":"2013","unstructured":"Brooke, J.: SUS: A retrospective. J. Usability Studies 8, 29\u201340 (2013)","journal-title":"J. Usability Studies"},{"key":"608_CR5","doi-asserted-by":"crossref","unstructured":"Cao, J., Chen, Z., Wu, J., et al.: JavaBench: A benchmark of object-oriented code generation for evaluating large language models. In: ASE. ACM, pp. 870\u2013882 (2024). See also https:\/\/github.com\/java-bench\/JavaBench","DOI":"10.1145\/3691620.3695470"},{"key":"608_CR6","unstructured":"Contreras, A., Guerra, E., de Lara, J.: Integrating conversational assistants within software development environments: An extensible approach. In: Extended and Selected papers of ENASE\u201924, pp. 1\u201328. Springer, CCIS (2025)"},{"key":"608_CR7","doi-asserted-by":"crossref","unstructured":"Contreras, A., Guerra, E., de Lara, J.: Conversational assistants for software development: Integration, traceability and coordination. In: ENASE. SCITEPRESS, pp. 27\u201338 (2024)","DOI":"10.5220\/0012561600003687"},{"issue":"2","key":"608_CR8","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/MS.2021.3133805","volume":"39","author":"NA Ernst","year":"2022","unstructured":"Ernst, N.A., Bavota, G.: AI-driven development is here: Should you worry? IEEE Softw. 39(2), 106\u2013110 (2022)","journal-title":"IEEE Softw."},{"key":"608_CR9","volume-title":"Contributing to Eclipse - principles, patterns, and plug-ins","author":"E Gamma","year":"2004","unstructured":"Gamma, E., Beck, K.L.: Contributing to Eclipse - principles, patterns, and plug-ins. Addison-Wesley, The Eclipse series (2004)"},{"key":"608_CR10","doi-asserted-by":"crossref","unstructured":"He, X., Li, D., Wen, H., et al.: CoSEFA: An LLM-based programming assistant for secure code generation via supervised co-decoding. In: FSE. ACM, pp. 1198\u20131202 (2025)","DOI":"10.1145\/3696630.3728609"},{"key":"608_CR11","doi-asserted-by":"crossref","unstructured":"He, J., Vechev, M.: Large language models for code: Security hardening and adversarial testing. In: CCS. ACM, pp. 1865\u20131879 (2023)","DOI":"10.1145\/3576915.3623175"},{"issue":"8","key":"608_CR12","doi-asserted-by":"publisher","first-page":"220:1","DOI":"10.1145\/3695988","volume":"33","author":"X Hou","year":"2024","unstructured":"Hou, X., Zhao, Y., Liu, Y., et al.: Large language models for software engineering: A systematic literature review. ACM Trans. Softw. Eng. Methodol. 33(8), 220:1-220:79 (2024)","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"608_CR13","unstructured":"Jiang, J., Wang, F., Shen, J., et al.: A survey on large language models for code generation. ArXiv e-prints arXiv:2406.00515 (2024)"},{"key":"608_CR14","doi-asserted-by":"crossref","unstructured":"Krishna, R., Pan, R., Sinha, S., et al.: CodeLLM-Devkit: A framework for contextualizing code LLMs with program analysis insights. In: FSE. ACM, pp. 308\u2013318 (2025)","DOI":"10.1145\/3696630.3728555"},{"key":"608_CR15","doi-asserted-by":"crossref","unstructured":"Leung, M., Murphy, G.: On automated assistants for software development: The role of LLMs. In: ASE. IEEE, pp. 1737\u20131741 (2023)","DOI":"10.1109\/ASE56229.2023.00035"},{"key":"608_CR16","unstructured":"Li, R., Allal, L.B., Zi, Y., et al.: StarCoder: May the source be with you! Trans. Mach. Learn. Res. (2023)"},{"key":"608_CR17","doi-asserted-by":"crossref","unstructured":"Liang, J.T., Yang, C., Myers, B.A.: A large-scale survey on the usability of AI programming assistants: Successes and challenges. In: ICSE. ACM, pp. 52:1\u201352:13 (2024)","DOI":"10.1145\/3597503.3608128"},{"key":"608_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Peng, Y., Huo, Y., et al.: Enhancing LLM-based coding tools through native integration of IDE-derived static context. In: LLM4Code. ACM, pp. 70\u201374 (2024)","DOI":"10.1145\/3643795.3648392"},{"issue":"2","key":"608_CR19","doi-asserted-by":"publisher","first-page":"39:1","DOI":"10.1145\/3695868","volume":"43","author":"X Li","year":"2025","unstructured":"Li, X., Wang, H., Liu, Z., et al.: Building a coding assistant via the retrieval-augmented language model. ACM Trans. Inf. Syst. 43(2), 39:1-39:25 (2025)","journal-title":"ACM Trans. Inf. Syst."},{"key":"608_CR20","doi-asserted-by":"crossref","unstructured":"Mathews, N.S., Nagappan, M.: Test-driven development and LLM-based code generation. In: ASE. ACM, pp. 1583\u20131594 (2024)","DOI":"10.1145\/3691620.3695527"},{"key":"608_CR21","unstructured":"Microsoft.: Language server protocol (2025). https:\/\/microsoft.github.io\/language-server-protocol\/"},{"key":"608_CR22","doi-asserted-by":"crossref","unstructured":"Mozannar, H., Bansal, G., Fourney, A., et al.: Reading between the lines: Modeling user behavior and costs in AI-assisted programming. In: CHI. ACM, pp. 142:1\u2013142:16 (2024a)","DOI":"10.1145\/3613904.3641936"},{"key":"608_CR23","doi-asserted-by":"crossref","unstructured":"Mozannar H, Bansal G, Fourney A, et al. (2024b) When to show a suggestion? Integrating human feedback in AI-assisted programming. In: AAAI. AAAI Press, pp 10137\u201310144","DOI":"10.1609\/aaai.v38i9.28878"},{"key":"608_CR24","doi-asserted-by":"crossref","unstructured":"Mu\u015flu, K., Brun, Y., Holmes, R., et al.: Speculative analysis of integrated development environment recommendations. In: OOPSLA. ACM, pp. 669\u2013682 (2012)","DOI":"10.1145\/2384616.2384665"},{"key":"608_CR25","unstructured":"Nghiem, K., Nguyen, A.M., Bui, N.D.Q.: Envisioning the next-generation AI coding assistants: Insights & proposals. ArXiv e-prints arXiv:2403.14592 (2024)"},{"key":"608_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2025.107737","volume":"183","author":"J Oertel","year":"2025","unstructured":"Oertel, J., Kl\u00fcnder, J., Hebig, R.: Don\u2019t settle for the first! How many GitHub Copilot solutions should you check? Inf. Softw. Technol. 183, 107737 (2025)","journal-title":"Inf. Softw. Technol."},{"key":"608_CR27","doi-asserted-by":"crossref","unstructured":"Pinto, G., De Souza, C., Neto, J.B., et al.: Lessons from building StackSpot AI: A contextualized AI coding assistant. In: ICSE-SEIP. ACM, pp 408\u2013417 (2024)","DOI":"10.1145\/3639477.3639751"},{"key":"608_CR28","unstructured":"Rozi\u00e8re, B., Gehring, J., Gloeckle, F., et al.: Code Llama: Open foundation models for code. ArXiv e-prints arXiv:2308.12950 (2023)"},{"issue":"8","key":"608_CR29","doi-asserted-by":"publisher","first-page":"221:1","DOI":"10.1145\/3680471","volume":"33","author":"D Russo","year":"2024","unstructured":"Russo, D.: Navigating the complexity of generative AI adoption in software engineering - RCR report. ACM Trans. Softw. Eng. Methodol. 33(8), 221:1-221:5 (2024)","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"608_CR30","doi-asserted-by":"crossref","unstructured":"Sainz, O., Campos, J.A., Garc\u00eda-Ferrero, I., et al.: NLP evaluation in trouble: On the need to measure LLM data contamination for each benchmark. In: EMNLP (Findings). ACL, pp 10776\u201310787 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.722"},{"key":"608_CR31","unstructured":"Sapkota, R., Roumeliotis, K.I., Karkee, M.: Vibe coding vs. agentic coding: Fundamentals and practical implications of agentic ai. arXiv:2505.19443 (2025)"},{"key":"608_CR32","doi-asserted-by":"crossref","unstructured":"Sauvola, J.J., Tarkoma, S., Klemettinen, M., et al.: Future of software development with generative AI. Autom. Softw. Eng. 31(1), 26 (2024)","DOI":"10.1007\/s10515-024-00426-z"},{"key":"608_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2024.107610","volume":"178","author":"A Sergeyuk","year":"2025","unstructured":"Sergeyuk, A., Golubev, Y., Bryksin, T., et al.: Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forward. Inf. Softw. Technol. 178, 107610 (2025)","journal-title":"Inf. Softw. Technol."},{"key":"608_CR34","unstructured":"Sergeyuk, A., Titov, S., Izadi, M.: In-IDE human-AI experience in the era of large language models; A literature review. In: IDE Workshop. ACM, pp. 95\u2013100 (2024)"},{"key":"608_CR35","unstructured":"Silas, M.: LSP-AI (2025). https:\/\/github.com\/SilasMarvin\/lsp-ai"},{"issue":"2","key":"608_CR36","first-page":"101","volume":"25","author":"A Vargha","year":"2000","unstructured":"Vargha, A., Delaney, H.D.: A critique and improvement of the cl common language effect size statistics of mcgraw and wong. J. Educ. Behav. Stat. 25(2), 101\u2013132 (2000)","journal-title":"J. Educ. Behav. Stat."},{"issue":"2","key":"608_CR37","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/s10515-025-00544-2","volume":"32","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Zhong, W., Huang, Y., et al.: Agents in software engineering: survey, landscape, and vision. Autom. Softw. Eng. 32(2), 70 (2025)","journal-title":"Autom. Softw. Eng."},{"key":"608_CR38","doi-asserted-by":"crossref","unstructured":"Wang, R., Cheng, R., Ford, D., et al.: Investigating and designing for trust in AI-powered code generation tools. In: FAccT. ACM, pp. 1475\u20131493 (2024)","DOI":"10.1145\/3630106.3658984"},{"key":"608_CR39","doi-asserted-by":"crossref","unstructured":"Weisz, J.D., Kumar, S.V., Muller, M., et al.: Examining the use and impact of an AI code assistant on developer productivity and experience in the enterprise. In: CHI Extended Abstracts. ACM, pp 673:1\u2013673:13 (2025)","DOI":"10.1145\/3706599.3706670"},{"issue":"6","key":"608_CR40","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bull. 1(6), 80\u201383 (1945)","journal-title":"Biometrics Bull."},{"key":"608_CR41","doi-asserted-by":"crossref","unstructured":"Xu, W., Gao, K., He, H., et al.: Licoeval: Evaluating LLMs on license compliance in code generation. In: ICSE. IEEE, pp. 1665\u20131677 (2025b)","DOI":"10.1109\/ICSE55347.2025.00052"},{"key":"608_CR42","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, H., Yang, Y., et al.: One size does not fit all: Investigating efficacy of perplexity in detecting LLM-generated code. ACM Trans. Softw. Eng. Methodol. Just Accepted (2025a)","DOI":"10.1145\/3748506"},{"key":"608_CR43","unstructured":"Zhao, W.X., Zhou, K., Li, J., et al.: A survey of large language models. ArXiv e-prints arXiv:2303.18223 (2023)"},{"key":"608_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, S., Zhu, A., Mozannar, H., et al.: CodingGenie: A proactive LLM-powered programming assistant. In: FSE. ACM, pp. 1168\u20131172 (2025)","DOI":"10.1145\/3696630.3728603"}],"container-title":["Automated Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-026-00608-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10515-026-00608-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-026-00608-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T14:33:02Z","timestamp":1778855582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10515-026-00608-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["608"],"URL":"https:\/\/doi.org\/10.1007\/s10515-026-00608-x","relation":{},"ISSN":["0928-8910","1573-7535"],"issn-type":[{"value":"0928-8910","type":"print"},{"value":"1573-7535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"8 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"63"}}