Governed Agentic RAG for Secure Enterprise Automation
DOI:
https://doi.org/10.5281/zenodo.21411983Keywords:
Enterprise Automation, Multi Agent, Retrieval Augmented, AI Systems, Agent Architecture, Data Retrieval, Knowledge Systems, Decision Making, Data Governance, Data Provenance, System Security, Risk Mitigation, Policy Enforcement, Scalable Systems, Modular Design, Open Interfaces, Information Access, Query Processing, System Evaluation, Intelligent Systems.Abstract
Automating enterprise operations offers the promise of substantially increased agility and competitive advantage. However, enterprises are still constrained in their ability to leverage such innovations for many operations beyond routine transaction processing. Security and oversight requirements ordinarily preclude the deployment of advanced AI techniques in data-rich enterprise context. Recently proposed retrieval-augmented AI designs provide a means to address some of these limitations, enabling formal institutions to enforce policy and mitigate risk, even when operations require complex reasoning and data synthesis. Yet no formal framework for retrieval-augmented multi-agent systems exists. Such a framework is necessary to support comprehensive validation and evaluation of emerging systems while also guiding practical implementations. Providing such an underpinning constitutes the principal contribution of this work.
The contributions of this study formalize the design of retrieval-augmented multi-agent systems. A foundation architectural model is defined, linking agent modularity, open interfaces, and scalable operation to retrieval-augmented operation. Grounding the architecture for enterprise contexts supports a comprehensive theory of retrieval-augmented multi-agent systems. Security and governed operation are addressed via consideration of (1) agent role definitions; (2) data access and provenance management; (3) strategic behaviour, information source maintenance, and understandable queries. Together, these aspects provide the procedural scaffolding necessary for scientifically-grounded operational and performance evaluations, endorsing the continued development of novel retrieval-augmented multi-agent systems for enterprise automation.
References
1. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2023). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. arXiv preprint arXiv:2310.11511.
2. Es, S., James, J., Espinosa-Anke, L., & Schockaert, S. (2023). RAGAS: Automated evaluation of retrieval augmented generation. arXiv preprint arXiv:2309.15217.
3. Izacard, G., et al. (2023). Atlas: Few-shot learning with retrieval augmented language models. Journal of Machine Learning Research, 24(233), 1–43.
4. Garapati, R. S., Aitha, A. R., Yandamuri, U. S., Gottimukkala, V. R. R., Nagubandi, A. R., & Kolla, S. H. (2026, March). Cloud-Native Orchestration of Multi-Counterparty Derivatives and Collateral in Manufacturing Enterprises via AI-Assisted Financial Audit Engines. In 2026 IEEE International Conference on AI Engineering and Innovations (AIEI) (pp. 1-6). IEEE.
5. Lewis, P., Perez, E., Piktus, A., et al. (2023). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems.
6. Gao, Y., Li, Y., & Xu, J. (2023). Enterprise applications of retrieval-augmented generation: Challenges and best practices. IEEE Transactions on Knowledge and Data Engineering.
7. Sun, L., Chen, H., et al. (2023). Evaluating metrics for enterprise RAG systems. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
8. Mangalampalli, B. M., & Kolla, T. (2026). FHIR-Based Interoperability Frameworks For Real-Time Healthcare Data Exchange: Architecture Patterns And Performance Optimization. International Journal Of Advances in Signal and Image Sciences, 1514-1536.
9. Jiang, Z., Ma, X., & Chen, W. (2024). LongRAG: Enhancing retrieval-augmented generation with long-context LLMs. arXiv preprint arXiv:2406.15319.
10. Gu, Y., Touvron, H., et al. (2024). Evaluation of retrieval-augmented generation: A survey. arXiv preprint arXiv:2405.07437.
11. Kolla, S. H., & Peddi, R. K. (2024). Designing Governance-Aligned GenAI Pipelines Using Small Language Models for Enterprise Workflow Intelligence. International Journal of Science, Research and Technology, 7(6), 13256-13268.
12. Huang, K., Wei, L., et al. (2024). Multimodal retrieval-augmented generation. Proceedings of the AAAI Conference on Artificial Intelligence.
13. Kolla, S. K., Bandi, V. D. V. K., & Meda, R. (2026). Comment on “Predicting self-image satisfaction after adult spinal deformity surgery: a machine learning approach using patient phenotypes”. Spine Deformity, 1-3.
14. Ponnuswamy, I., & Cayer, M. (2024). Retrieval-augmented generation: A cutting-edge AI technology for knowledge sharing in organizations? Academy of Management Proceedings, 2024(1).
15. Gaddam, M. K. (2024). Federated RAG architectures for distributed enterprise knowledge systems. Journal of Information Systems Engineering and Management.
16. Nagubandi, A. R. (2026). Governance, Transparency, and Trust in Intelligent Financial Systems. Cognitive Financial Infrastructure: Designing Adaptive, Integrated Market Systems. Deep Science Publishing. https://doi. org/10.70593/978-93-7185-062-9_9.
17. Yang, B., Huang, Z., et al. (2024). Improving precision in RAG with governance layers. International Conference on Learning Representations.
18. Wang, H., Zhang, J., & Liu, X. (2024). Policy-aware retrieval for enterprise AI systems. IEEE Access, 12, 102211–102227.
19. Chen, R., Gupta, A., & Singh, P. (2024). Explainable retrieval augmentation for enterprise compliance. Expert Systems with Applications, 245, 122845.
20. Singh, B., Garapati, R. S., Kumar, C., Madhubalan, S., & Chekuri, N. (2026, February). Behavior-Aware Edge-Based Zero-Trust Cybersecurity Framework for Securing Internet of Things Enabled Smart Home Environments. In 2026 3rd International Conference on Integrated Intelligence and Communication Systems (ICIICS) (pp. 1-5). IEEE.
21. Zhao, Y., Li, H., & Wang, Q. (2024). Secure retrieval pipelines for large language models. Future Generation Computer Systems, 157, 89–104.
22. Kolla, S. H. (2026). Autonomous Enterprise Agents: Orchestrating Large and Small Language Models for Scalable Decision Automation in ITSM, HRSD, and CSM Platforms. INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, 24-45.
23. Kim, J., Park, S., & Lee, H. (2024). Governance frameworks for enterprise generative AI deployment. Information Systems Frontiers, 26(5), 1671–1689
24. None, D. M. K., None, V. D. V. K. B., None, N. M., None, S. H. K., & None, B. M. M. (2026). Engineering Intelligent Cloud-Native Data Ecosystems for Predictive Decision-Making in Industry. Journal of European Economic History, 7(2), 68-88.
25. Patel, R., Kumar, S., & Verma, A. (2024). AI governance and compliance in regulated industries. Computers & Security, 139, 103615.
26. Singh, M., & Gupta, D. (2024). Trustworthy retrieval augmented generation for enterprise applications. IEEE Intelligent Systems, 39(6), 57–66.
27. Londhe, G. V., Thiyagarajan, R., Kirti, V., Nagabhyru, K. C., & Marar, S. S. (2026). ALGORITHMIC POWER AND CULTURAL RATIONALITY: HOW AI-DRIVEN DECISION SYSTEMS ARE REWRITING GOVERNANCE, MARKETS, AND ETHICAL RESPONSIBILITY. Scientific Culture, 12(1, Part 1), 4219.
28. Liu, X., Chen, T., & Wang, Z. (2024). Secure vector databases for enterprise AI. ACM Computing Surveys, 57(4), 1–36.
29. Klesel, H., & Matzner, M. (2025). Retrieval-augmented generation in information systems: Opportunities and challenges. Business & Information Systems Engineering.
30. Mattaparthi, R. (2022). Engineering Predictive Industrial Systems Through IoT-Driven Asset Monitoring and Machine Learning Prognostics. International Journal of Future Innovative Science and Technology (IJFIST), 5(1), 7790.
31. Kesuma, C. (2025). Retrieval augment generation governance architecture for enterprise information systems. International Journal of Informatics, Economics, Management and Science.
32. Karakurt, E., & Akbulut, A. (2025). Retrieval-augmented generation and large language models for enterprise knowledge management and document automation: A systematic literature review. Applied Sciences.
33. Bandi, V. D. V. K. (2026). Cognitive Data Engineering: AI-Governed Data Quality, Lineage, and Pipeline Optimization at Scale. International Journal of Economic Practices and Theories, 2026, 131-148.
34. Kurra, M. Y. (2025). Generative AI agents at enterprise scale: Architecting RAG-enhanced LLM systems for production deployment. International Journal of Computational Mathematical Ideas.
35. Kolla, S. H. (2023). Deep learning-driven retrieval-augmented generation for enterprise ITSM automation: A governance-aligned large language model architecture. Journal of Computational Analysis and Applications.
36. Cook, T., Osuagwu, R., Tsatiashvili, L., Vrynsia, V., Masoud, M., Mattivi, R., & Ghosal, K. (2025). Retrieval augmented generation for fintech: Agentic design and evaluation. arXiv preprint arXiv:2510.25518.
37. Romeo, F., Arena, L., Blefari, F., Pironti, F. A., Lupinacci, M., & Furfaro, A. (2025). ARPaCCino: An agentic-RAG for policy as code compliance. arXiv preprint arXiv:2507.10584.
38. Kolla, T. (2026). Multi-Agent AI Framework for Predictive Healthcare Interoperability. International Journal of Multidisciplinary Research in Science, Engineering, Technology & Management, 2(5), 1-15.
39. Byun, G., Lee, S., Choi, N., & Choi, J. (2025). Secure multifaceted-RAG for enterprise: Hybrid knowledge retrieval with security filtering. arXiv preprint arXiv:2504.13425.
40. Bargavi, N., Athawale, S. G., Amistapuram, K., & Aitha, A. R. (2026). Safeguarding Consumer Data in Digital Insurance: Legal Frameworks and Ethical Imperatives. International Insurance Law Review, 34(S1), 272-284.
41. Mishra, S., Niroula, S., Yadav, U., Thakur, D., Gyawali, S., & Gaire, S. (2026). SoK: Agentic retrieval-augmented generation (RAG): Taxonomy, architectures, evaluation, and research directions. arXiv preprint arXiv:2603.07379.
42. Rana, S. A. (2025). Exploring the role of retrieval-augmented generation in enhancing cybersecurity governance and risk compliance frameworks.
43. Rana, S. A. (2025). AI governance in smart grids and industrial automation: Integrating retrieval-augmented generation with framework mapping.
44. Segireddy, A. R., Nagabhyru, K. C., Gadi, A. L., Pandiri, L., Paleti, S., Nandan, B. P., ... & Meda, R. (2026). U.S. Patent Application No. 19/389,116.
45. Pandey, R. (2025). The agentic AI governance framework: A universal model for risk, accountability, and compliance in autonomous systems.
46. Malvone, V., Nguyen, V.-T., Perlić, V., Lebailly, S., & Urard, P. (2025). MMA-RAG: A survey on multimodal agentic retrieval-augmented generation.
47. Arena, L., Blefari, F., Furfaro, A., Lupinacci, M., Pironti, F. A., & Romeo, F. (2025). Agentic retrieval-augmented generation for automated compliance verification.
48. Zhou, P., Feng, Y., & Yang, Z. (2025). Secure and privacy-preserving architectures for retrieval-augmented generation systems.
49. Davuluri, P. N. (2026). Autonomous Compliance Systems: AI, Event Streaming, and the Future of Financial Crime Prevention. Journal of Informatics Education and Research.
50. Feng, Y., Yang, Z., & Zhou, P. (2025). Provably secure retrieval-augmented generation.
51. Singhal, T., Kelkar, A., Tuo, J., & Wang, C. L. (2025). MI9: Agent intelligence protocol for runtime governance in agentic AI systems.
52. Wang, P., Li, J., et al. (2025). Governance compliance metrics in enterprise RAG. IEEE Transactions on Information Systems.
53. Ahmed, S., & Ibrahim, M. (2025). Agentic AI architectures for enterprise process automation. IEEE Access.
54. Inala, R. (2026). Cloud-Native AI and MDM Framework for Next-Generation Insurance and Retirement Data Products. International Journal of Engineering & Extended Technologies Research (IJEETR), 8(3), 5050-5063.
55. Kumar, V., & Reddy, P. (2025). Governance-aware multi-agent systems for secure enterprise workflows. Future Internet.
56. Li, X., Zhao, Q., & Wang, H. (2025). Autonomous retrieval orchestration in enterprise RAG systems. Information Processing & Management.
57. Chen, Y., & Xu, M. (2025). AI guardrails for enterprise automation. Computers & Security.
58. Reddy, V. A. R. (2022). Data-Driven Healthcare Operations: Architecting Unified Member, Provider, and Claims Intelligence Platforms. International Journal of Science, Research and Technology, 5(5), 8511-8521.
59. Thomas, R., & Miller, J. (2025). Secure AI agents for business process automation. Journal of Systems and Software.
60. Park, S., Kim, J., & Lee, H. (2025). Agentic governance models for enterprise generative AI. Information Systems Frontiers.
61. Johnson, T., & Brown, D. (2025). Enterprise AI compliance through retrieval-enhanced reasoning. Expert Systems.
62. Gupta, A., Singh, R., & Verma, D. (2025). AI risk management for autonomous enterprise systems. IEEE Software.
63. Liu, J., & Chen, X. (2025). Explainability in agentic AI systems. Artificial Intelligence Review.
64. Yandamuri, U. S. (2026). Operational Intelligence Engineering: Integrated Systems for Smart Service and Production Sectors. Deep Science Publishing.
65. Sharma, N., & Kapoor, P. (2025). Secure orchestration of enterprise AI agents. Future Generation Computer Systems.
66. Davis, E., & Clark, M. (2025). Governance-by-design for enterprise LLM deployments. MIS Quarterly Executive.
67. Martin, P., & Wilson, K. (2025). Policy-driven AI workflow automation. Decision Support Systems.
68. Roberts, L., & Evans, S. (2025). Auditability and traceability in autonomous AI agents. Information & Management.
69. White, J., & Harris, B. (2025). Enterprise-scale retrieval systems for regulated environments. IEEE Internet Computing.
70. Amistapuram, K. (2026). Safeguarding Consumer Data in Digital Insurance: Legal Frameworks and Ethical Imperatives. Available at SSRN 6142748.
71. Zhao, H., & Wang, L. (2025). Access-control-aware retrieval augmentation. ACM Transactions on Information Systems.
72. Green, R., & Patel, N. (2025). Secure enterprise knowledge retrieval with LLMs. Knowledge-Based Systems.
73. Allen, T., & Young, C. (2025). Autonomous compliance monitoring using AI agents. Computers in Industry.
74. Brooks, D., & Foster, J. (2025). Governance-centric AI operations for enterprises. Journal of Enterprise Information Management.
75. Turner, M., & Scott, A. (2025). Risk-aware agentic systems in enterprise environments. AI & Society.
76. Bell, S., & Cooper, R. (2025). Enterprise security architectures for agentic AI. Computer Networks.
77. Nelson, G., & Reed, H. (2025). Dynamic policy enforcement in AI-driven enterprises. IEEE Transactions on Services Computing.
78. Baker, J., & Adams, F. (2025). Compliance-aware reasoning in enterprise language models. Expert Systems with Applications.
79. Morris, P., & Lewis, D. (2025). Enterprise governance frameworks for generative AI. Business Horizons.
80. Carter, A., & Hill, B. (2025). Secure retrieval infrastructures for enterprise automation. Information Systems Journal.
81. Evans, J., & Mitchell, S. (2025). Multi-agent orchestration for enterprise knowledge workflows. Journal of Intelligent Information Systems.
82. Walker, R., & Hughes, M. (2025). Trustworthy enterprise AI ecosystems. IEEE Intelligent Systems.
83. Stewart, K., & Rogers, T. (2025). Governance-ready autonomous enterprise agents. AI Magazine.
84. Collins, P., & Turner, D. (2025). Enterprise-grade retrieval augmented intelligence. Knowledge and Information Systems.
85. Foster, B., & White, R. (2025). Agentic automation for regulated business processes. Information & Software Technology.
86. Young, M., & Green, S. (2025). Secure LLM governance patterns for enterprises. Journal of Strategic Information Systems.
87. Reed, T., & Carter, P. (2025). AI assurance and compliance automation. Computers & Security.
88. Harris, J., & Scott, K. (2025). Agent-based enterprise intelligence architectures. Decision Analytics Journal.
89. Mitchell, D., & Brooks, S. (2025). Governance-enabled retrieval and reasoning systems for enterprise automation. International Journal of Information Management.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
This work is licensed under a Creative Commons
Attribution 4.0 International License (CC BY 4.0).
You are free to:
- Share: copy and redistribute the material
- Adapt: remix, transform, and build upon the material
for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit to
the original author(s) and source.
Full license text: https://creativecommons.org/licenses/by/4.0/
