A Conceptual Framework for Multi-Agent AI Quality Control in The Review of Regulated Documents
Abstract
Organizations in pharmaceutical, financial, and other regulated sectors face rising pressure to review large volumes of complex documents against strict and frequently evolving standards, while preserving the traceability needed to defend decisions to auditors and regulators. Large language model based automation offers clear efficiency gains, but single-agent deployments raise well-documented concerns about hallucination, opacity, and insufficient auditability, particularly as regulatory regimes such as the European Union Artificial Intelligence Act begin to impose explicit human oversight and logging obligations on high-risk systems. This paper proposes a conceptual framework for multi-agent AI quality control in the review of regulated documents. The framework decomposes the review task across specialized agents, including extraction, domain compliance checking, adversarial cross-validation, audit and traceability, and human interface functions, coordinated by an orchestrator and grounded in a governed regulatory knowledge base. We describe design principles, architecture, a step-by-step workflow, quality control mechanisms such as confidence scoring and entailment-based cross-checking, and evaluation metrics suited to regulated settings. An illustrative scenario drawn from pharmaceutical Good Practice document review demonstrates the framework in use, and a secondary example from financial disclosure review indicates its generality. We close with a discussion of open challenges, including correlated error propagation across agents built on shared foundation models, computational overhead, regulatory acceptance, and security risks such as prompt injection, and we outline directions for empirical validation.
Keywords
multi-agent systemslarge language modelsquality controlregulated documentsAI governancecompliance automationhuman oversightauditability
References
Adebayo, A., Adepoju, P. A., & Ozowara, D. E. (2023). Conceptual model for cyber risk pricing and insurance structuring in health technology platforms. Gyanshauryam, International Scientific Refereed Research Journal, 6(6), 601-624. Adeyelu, O. O. (2023). A risk-tiered oversight model for unmanned aircraft operations in shared controlled airspace over Nigerian airports. International Journal of Scientific Research in Civil Engineering, 7(4), 147-184. Afrihyia, E., Akinse, S. G., & Ojukwu, P. U. (2024). Comparative governance of AI-driven healthcare management: Executive oversight, regulatory structures, and accountability in the United States and developing countries. International Journal of Advanced Multidisciplinary Research and Studies, 4(6), 3087-3102. Afrihyia, E., Akinse, S. G., & Ojukwu, P. U. (2025). Organizational readiness for generative AI integration in healthcare operations: Comparative management capabilities between the U.S. and low- and middle-income countries. Iconic Research and Engineering Journals, 8(10), 1673-1697. Akintola, A. S., Fawehinmi, Y. O., Aiyenitaju, O., Chinemerem, B., & Emmanuella, O. (2025). Digital transformation in telehealth: A systematic review of user trust, privacy, and regulatory governance in AI-powered remote monitoring systems. Journal of Scientific Research and Reports, 31(11), 163-182. Akomolafe, O., & Agu, M. U. (2018). A conceptual model for enhancing internal audit quality through technology-enabled risk assessment frameworks. Iconic Research and Engineering Journals, 1(9), 458-475. Akomolafe, O., & Agu, M. U. (2019a). A conceptual framework for developing risk-based internal control models in the insurance and banking sectors. Iconic Research and Engineering Journals, 2(8), 335-354. Akomolafe, O., Agu, M. U., & Bello, A. (2025). A conceptual model for advancing risk governance through data-driven compliance analytics in financial institutions. Journal of Accounting and Financial Management, 11(11), 211-228. Aliliele, C., Mbonu, I. S., & Iwuanyanwu, U. (2023a). A conceptual framework for continuous cloud misconfiguration monitoring and enterprise risk mitigation strategies. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 9(10), 373-394. Aliliele, C., Mbonu, I. S., & Iwuanyanwu, U. (2024a). A conceptual framework for enterprise data sensitivity classification and regulatory traceability mechanisms. International Journal of Advanced Multidisciplinary Research and Studies, 4(6), 3103-3124. Aliliele, C., Mbonu, I. S., Uzoka, E., & Iwuanyanwu, U. (2025a). A review of AI assisted continuous auditing systems in technology risk and cybersecurity oversight. Gyanshauryam, International Scientific Refereed Research Journal, 8(4), 210-250. Aliliele, C., Mbonu, I. S., Uzoka, E., & Iwuanyanwu, U. (2025b). Advances in data lakehouse governance architectures for enterprise data loss prevention and compliance assurance. Shodhshauryam, International Scientific Refereed Research Journal, 8(4), 171-213. Annan, A. O. (2023). Intellectual property ownership and authorship in AI-generated works. Gyanshauryam, International Scientific Refereed Research Journal, 6(3), 425-450. Annan, A. O. (2024). Algorithmic accountability and trade secret protection in artificial intelligence. Shodhshauryam, International Scientific Refereed Research Journal, 7(5), 315-347. Annan, A. O. (2025a). Automated decision-making and anti-discrimination compliance under U.S. law. International Journal of Advanced Multidisciplinary Research and Studies, 5(2), 2522-2540. Annan, A. O. (2025b). Cybersecurity compliance as a source of competitive advantage in technology markets. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 11(5), 456-487. AO Shearman. (2024). EU AI Act: Obligations for high-risk AI systems. AO Shearman Insights on Tech. Article 14: Human Oversight. (n.d.). EU Artificial Intelligence Act. artificialintelligenceact.eu. Atakpa, M. I., & Abolaji, T. O. (2022). A privacy-preserving data architecture model for regulated industry analytics under GDPR and HIPAA compliance. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 8(3), 781-808. Badmus, O., Dosunmu, A. A., & Anunagba, C. O. (2025). A governance framework for AI- assisted CRM workflows: Agentforce deployment, risk management, and organizational readiness in enterprise Salesforce environments. International Journal of Scientific Research in Humanities and Social Sciences, 2(1), 59-80. Badmus, O., Jooda, D., & Anunagba, C. O. (2024). A privacy-by-design framework for role-based security architecture in Salesforce environments handling sensitive personal data. International Journal of Advanced Multidisciplinary Research and Studies, 4(6), 3244- 3254. Dosunmu, A. A., & Ogundele, P. O. (2024a). Breach and attack simulation frameworks for continuous validation of enterprise security controls. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10(3), 1100- 1119. Dosunmu, A. A., & Ogundele, P. O. (2024c). Enterprise scale continuous security validation models for regulated digital infrastructures. International Journal of Scientific Research in Humanities and Social Sciences, 1(2), 929-945. Edivri, J., & Oteri, O. (2022). Predictive capacity planning and resource utilization forecasting models for multi-program and multi-stakeholder IT portfolios. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 8(4), 826-845. Eularis. (2024). Reducing hallucinations in LLMs. Eularis Insights. Eze, F. I., Akinleye, O. K., & Anene, U. N. (2024a). Development of a cross-border regulatory harmonization model for African pharmaceutical markets: The ARCH-Model framework. International Journal of Health and Pharmaceutical Research, 9(5), 148-186. Eze, F. I., Akinleye, O. K., & Anene, U. N. (2024b). Development of a risk-based accelerated approval decision model balancing speed, safety, and evidence quality in pharmaceutical regulatory science. Research Journal of Pure Science and Technology, 7(6), 120-161. Eze, F. I., Anene, U. N., & Akinleye, O. K. (2022a). Creation of a drug shortage early warning and regulatory response model for essential medicines in global health systems. Research Journal of Pure Science and Technology, 5(1), 57-95. Eze, F. I., Anene, U. N., & Akinleye, O. K. (2022b). Design of an integrated regulatory readiness maturity model for pharmaceutical companies seeking global market entry. International Journal of Health and Pharmaceutical Research, 7(1), 77-112. Eze, F. I., Anene, U. N., & Akinleye, O. K. (2023). Pharmaceutical supply chain governance, environmental risk management, and sustainable access to essential medicines in emerging economies: The PSCG-ERM framework. International Journal of Health and Pharmaceutical Research, 8(4), 192-241. Fobellah, A. N. (2025a). Cognitive biases in financial decision-making: Implications for audit and risk management in large corporations: A conceptual review. International Journal of Science and Research Archive, 16(2), 17-22. Fobellah, A. N. (2025b). Navigating digital transformation: Auditing artificial intelligence- powered financial systems: A conceptual review. International Journal of Science and Research Archive, 16(2), 23-28. Governance-as-a-Service: A multi-agent framework for AI system compliance and policy enforcement. (2025). Preprint. IONI. (2025). Multi-AI agents systems in 2025: Key insights, examples, and challenges. IONI.ai. Ladapo, O. O., Dosunmu, A. A., Jooda, D., & Abolaji, T. O. (2022). Human-in-the-loop machine learning: A state of the art. Journal of Frontiers in Multidisciplinary Research, 3(1), 656- 669. Ladapo, O. O., Jooda, D., Dosunmu, A. A., & Abolaji, T. O. (2024). Keeping humans in the loop: Human-centered automated annotation with generative AI. International Journal of Multidisciplinary Futuristic Development, 5(1), 81-95. Mbonu, I. S., Aliliele, C., Iwuanyanwu, U., & Oluoha, O. M. (2018). A conceptual framework for legal and ethical risk modeling in enterprise data protection governance systems. Iconic Research and Engineering Journals, 2(2), 207-226. Mbonu, I. S., Aliliele, C., Iwuanyanwu, U., & Uzoka, E. (2021b). Advances in artificial intelligence techniques for secure software testing and automated regression control mechanisms. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 7(5), 468-496. Mbonu, I. S., Aliliele, C., Iwuanyanwu, U., & Uzoka, E. (2022). A conceptual framework for AI enabled IT general controls and SOX audit automation processes. Gyanshauryam, International Scientific Refereed Research Journal, 5(5), 384-414. Odejobi, O. D., Okonkwo, C. S., Ahiaeke Patrick, M. C., Okeke, O. T., & Mayo, W. (2025). AI- augmented secure software engineering: Leveraging deep learning for autonomous threat detection and mitigation. International Journal of Engineering and Modern Technology, 11(12), 101-121. Onche, V. O., Ogbonna, C. S., & Adegbite, M. P. (2024). Effectiveness of cybersecurity awareness training on insider-threat behavior among university administrators: An integrative academic review. International Journal of Computer Science and Mathematical Theory, 10(2), 117-144. Oteri, O., & Edivri, J. (2024). Applied performance optimization frameworks for managing high- demand enterprise technology programs and system rollouts. Gyanshauryam, International Scientific Refereed Research Journal, 7(1), 188-210. Ozowara, D. E., Adebayo, A., & Anunagba, C. O. (2025). Advanced conceptual model for strengthening audit quality using data analytics across financial institutions. International Journal of Advanced Multidisciplinary Research and Studies, 5(6), 2246-2268. Robertson, Z., et al. (2025). Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025. arXiv preprint. Sanni, J. O., Iwuanyanwu, U. A., Essien, M. A., Atima, M. E., & Attah, A. (2022). Adaptive control models for AI-driven marketing automation in financial compliance environments. Shodhshauryam, International Scientific Refereed Research Journal, 5(1), 243-270. Sanni, J. O., Iwuanyanwu, U. A., & Essien, M. A. (2025). Problem-oriented process mining for auditable marketing automation lifecycle control. International Journal of Advanced Multidisciplinary Research and Studies, 5(6), 1933-1947.
More Articles from INTERNATIONAL JOURNAL OF SOCIAL SCIENCES AND MANAGEMENT RESEARCH
Organizational Culture and Employee Wellbeing in Rivers State University
Author: Josephine U. Mkpong Prof. Emmanuel B. Okemini
Industrial Training and Labour Efficiency in Selected Public Enterprises in Rivers State, Nigeria
Author: Nma Owere Prof. E.B Okemini C.D Chukwu PhD
Green Strategic Management and Organizational Performance of Manufacturing Firms in Cross River State, Nigeria
Author: Diwa Damian Odu, Godwin Ititim Undie, Egede David Aganyi, Abiji, Emmanuel Abiji
Determining Strategic Methods for Post-Fire Disaster Recovery in the Major Markets in Port Harcourt Metropolis, Rivers State
Author: Onuegbu, W. C., Igbanam, E. S. Kimone O.
Socio-Cultural Determinants of Attitudes Towards Contraceptive Use Among Female Undergraduates in Tertiary Institutions in the Southern Senatorial District of Plateau State
Author: Joseph Taiye Ezekiel, Ojo Kayode Ayobami PhD