{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T09:58:32Z","timestamp":1791971912550,"version":"4.3.4"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Luxembourg National Research Fund","award":["grant reference NCER22\/IS\/16570468\/NCER-FT"],"award-info":[{"award-number":["grant reference NCER22\/IS\/16570468\/NCER-FT"]}]},{"name":"SERICS","award":["PE00000014\u2014CUP H73C2200089001"],"award-info":[{"award-number":["PE00000014\u2014CUP H73C2200089001"]}]},{"name":"PNRR","award":["Mission 4.2, Investment 49 1.5"],"award-info":[{"award-number":["Mission 4.2, Investment 49 1.5"]}]},{"name":"NextGeneration EU","award":["ECS_00000043\u2014CUP H43C22000540006"],"award-info":[{"award-number":["ECS_00000043\u2014CUP H43C22000540006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:p>Ensuring compliance with regulations poses considerable challenges for software development, particularly during the requirements specification phase. Traditional methods rely heavily on manual inspections that are time-consuming and prone to errors. This research proposes an innovative framework that leverages the synergy of multiple AI agents to automate software requirement compliance verification partially. The framework integrates Large Language Models (LLMs), prompt engineering, and Retrieval-Augmented Generation (RAG) to analyze, detect, and revise non-compliant requirements. The core of our proposal lies in multi-agent communication, where distinct AI agents collaborate to achieve the overarching goal of compliance checking. LLMs comprehend requirements specifications, while prompt engineering guides LLMs toward compliance-related aspects. The RAG techniques detect non-compliant requirements and suggest changes. Finally, a robust Human-in-the-Loop mechanism ensures accuracy, reliability, and adaptability. A tool, available online, is implemented to translate the technology for effective application. We discuss its ability to identify non-compliant requirements in an extensive experimental evaluation.<\/jats:p>","DOI":"10.1145\/3785472","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T14:30:36Z","timestamp":1766413836000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["A Multi-Agent RAG Framework for Regulatory Compliance Checking of Software Requirements"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3314-2537","authenticated-orcid":false,"given":"Souvick","family":"Das","sequence":"first","affiliation":[{"name":"Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Kirchberg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3680-3625","authenticated-orcid":false,"given":"Novarun","family":"Deb","sequence":"additional","affiliation":[{"name":"Electrical and Software Engineering, University of Calgary, Calgary, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3242-680X","authenticated-orcid":false,"given":"Nabendu","family":"Chaki","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Calcutta, Kolkata, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0946-5440","authenticated-orcid":false,"given":"Agostino","family":"Cortesi","sequence":"additional","affiliation":[{"name":"Environmental Sciences Informatics and Statistics, Ca\u2019 Foscari University of Venice, Mestre, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3465481.3470031"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/REW53955.2021.00009"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3124332"},{"key":"e_1_3_2_5_2","first-page":"4282","article-title":"Nlp-based automated compliance checking of data processing agreements against gdpr","author":"Amaral Orlando","year":"2023","unstructured":"Orlando Amaral, Muhammad Ilyas Azeem, Sallam Abualhaija, and Lionel C. Briand. 2023. Nlp-based automated compliance checking of data processing agreements against gdpr. IEEE Transactions on Software Engineering 49, 9 (2023), 4282\u20134303.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_6_2","unstructured":"AI Anthropic. 2024. Introducing the Next Generation of Claude. Retrieved from https:\/\/www.anthropic.com\/news\/claude-3-family"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Chetan Arora Tomas Herda and Verena Homm. 2024. Generating test scenarios from NL requirements using retrieval-augmented LLMs: An industrial study. In 2024 IEEE 32nd International Requirements Engineering Conference (RE). IEEE 240\u2013251.","DOI":"10.1109\/RE59067.2024.00031"},{"key":"e_1_3_2_8_2","unstructured":"Muhammad Ilyas Azeem and Sallam Abualhaija. 2023. A multi-solution study on GDPR AI-enabled completeness checking of DPAs. arXiv:2311.13881. Retrieved from https:\/\/arxiv.org\/abs\/2311.13881"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1036"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386518"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-020-00677-4"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2006.68"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual multi-functionality multi-granularity text embeddings through self-knowledge distillation. arXiv:2402.03216. Retrieved from https:\/\/arxiv.org\/abs\/2402.03216","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_14_2","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv:2507.06261. Retrieved from https:\/\/arxiv.org\/abs\/2507.06261"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2024.3416036"},{"key":"e_1_3_2_16_2","unstructured":"Shahul Es Jithin James Luis Espinosa-Anke and Steven Schockaert. 2023. Ragas: Automated evaluation of retrieval augmented generation. arXiv:2309.15217. Retrieved from https:\/\/arxiv.org\/abs\/2309.15217"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00032"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE57278.2023.00045"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2017.29"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835639"},{"key":"e_1_3_2_21_2","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra Singh Chaplot Diego de las Casas Emma Bou Hanna Florian Bressand et al. 2024. Mixtral of experts. arXiv:2401.04088. Retrieved from https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87877-3_13"},{"key":"e_1_3_2_23_2","unstructured":"Robert Lakatos Peter Pollner Andras Hajdu and Tamas Joo. 2024. Investigating the performance of retrieval-augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems. arXiv:2403.09727. Retrieved from https:\/\/arxiv.org\/abs\/2403.09727"},{"key":"e_1_3_2_24_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-Tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_25_2","unstructured":"Xueguang Ma Kai Sun Ronak Pradeep and Jimmy Lin. 2021. A replication study of dense passage retriever. arXiv:2104.05740. Retrieved from https:\/\/arxiv.org\/abs\/2104.05740"},{"key":"e_1_3_2_26_2","unstructured":"Niklas Muennighoff Nouamane Tazi Lo\u00efc Magne and Nils Reimers. 2022. MTEB: Massive text embedding benchmark. arXiv:2210.07316. Retrieved from https:\/\/arxiv.org\/abs\/2210.07316"},{"key":"e_1_3_2_27_2","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage re-ranking with BERT. arXiv:1901.04085. Retrieved from https:\/\/arxiv.org\/abs\/1901.04085"},{"key":"e_1_3_2_28_2","first-page":"101","article-title":"Modelling legal knowledge for GDPR compliance checking","volume":"313","author":"Palmirani Monica","year":"2018","unstructured":"Monica Palmirani and Guido Governatori. 2018. Modelling legal knowledge for GDPR compliance checking. JURIX 313 (2018), 101\u2013110.","journal-title":"JURIX"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.114013"},{"key":"e_1_3_2_30_2","unstructured":"Catherine Sai Shazia Sadiq Lei Han Gianluca Demartini and Stefanie Rinderle-Ma. 2024. Identification of regulatory requirements relevant to business processes: A comparative study on generative AI embedding-based ranking crowd and expert-driven methods. arXiv:2401.02986. Retrieved from https:\/\/arxiv.org\/abs\/2401.02986"},{"key":"e_1_3_2_31_2","unstructured":"Aamir Shakir Darius Koenig Julius Lipp and Sean Lee. 2024. Boost Your Search With The Crispy Mixedbread Rerank Models. Retrieved from https:\/\/www.mixedbread.com\/blog\/mxbai-rerank-v1"},{"key":"e_1_3_2_32_2","unstructured":"Supreeth Shastri Melissa Wasserman and Vijay Chidambaram. 2019. GDPR anti-patterns: How design and operation of modern cloud-scale systems conflict with GDPR. arXiv:1911.00498. Retrieved from https:\/\/arxiv.org\/abs\/1911.00498"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2018.00022"},{"key":"e_1_3_2_34_2","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. Retrieved from https:\/\/crfm.stanford.edu\/2023\/03\/13\/alpaca.html"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Nandan Thakur Nils Reimers Johannes Daxenberger and Iryna Gurevych. 2020. Augmented SBERT: Data augmentation method for improving bi-encoders for pairwise sentence scoring tasks. arXiv:2010.08240. Retrieved from https:\/\/arxiv.org\/abs\/2010.08240","DOI":"10.18653\/v1\/2021.naacl-main.28"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3372194"},{"key":"e_1_3_2_37_2","first-page":"233","volume-title":"Proceedings of the 35th International Conference on Conceptual Modeling (ER \u201916)","author":"Zeni Nicola","year":"2016","unstructured":"Nicola Zeni, Elias A. Seid, Priscila Engiel, Silvia Ingolfo, and John Mylopoulos. 2016. Building large models of law with N\u00f3mosT. In Proceedings of the 35th International Conference on Conceptual Modeling (ER \u201916). Springer, 233\u2013247."}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3785472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T11:14:21Z","timestamp":1784978061000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":36,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,31]]}},"alternative-id":["10.1145\/3785472"],"URL":"https:\/\/doi.org\/10.1145\/3785472","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"2025-02-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}