Authors : Sujit Shibaprasad Maity

Volume/Issue : Volume 11 - 2026, Issue 10 - October

DOI : https://doi.org/10.38124/ijisrt/26Oct511

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Enterprises increasingly rely on heterogeneous documents, relational databases, and analytical systems to support information retrieval and business decision-making. Integrating large language models (LLMs) with these sources introduces challenges in evidence reliability, analytical correctness, access control, and operational resilience. This paper presents PIU Smart Intelligence Agents, a security-aware multi-agent architecture designed to integrate enterprise document intelligence, retrieval-augmented generation (RAG), semantic search, document summarization, naturallanguage-to-SQL analytics, key performance indicator (KPI) generation, and conversational AI within a common application and governance framework. The proposed architecture organizes specialized AI capabilities around shared services for authentication, authorization, request validation, provider integration, observability, and controlled data access. Its document-processing workflow encompasses file validation, text extraction, optical character recognition for scanned documents, normalization, chunking, embedding generation, and vector-based indexing. The structured-analytics workflow separates schema-aware query generation from SQL validation, restricted database execution, and result interpretation. The architecture also addresses provider compatibility, timeout handling, failure recovery, document lifecycle management, and traceability of generated outputs. The source implementation reports 1,242 automated tests passed and two integration tests skipped. These results are reported implementation evidence and have not been independently reproduced. The available evidence does not establish comprehensive external RAG benchmark performance, quantitative correctness across all agents, independently validated security effectiveness, or production-scale performance and recovery guarantees. Accordingly, this study presents an integrated engineering architecture and identifies a reproducible evaluation framework for assessing its effectiveness. The principal contribution is the systematic integration of heterogeneous enterprise AI capabilities with explicit governance and validation requirements, rather than the introduction of a new learning or retrieval algorithm. Future work should prioritize agent-specific correctness testing, retrieval and answer-quality benchmarks, adversarial security evaluation, controlled load testing, and recovery verification.

Keywords : Enterprise Artificial Intelligence, Multi-Agent Systems, Retrieval-Augmented Generation, Intelligent Document Processing, Semantic Search, Natural-Language-To-SQL, KPI Generation, Conversational AI, Optical Character Recognition, Prompt Injection, Provider Resilience, Enterprise Security, AI Governance.

References :

1. P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-augmented generation for knowledge-intensive NLP tasks,” in Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020.
2. A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, vol. 30, 2017.
3. N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using Siamese BERT-networks,” in Proc. Conf. Empirical Methods in Natural Language Processing and 9th Int. Joint Conf. Natural Language Processing (EMNLP-IJCNLP), 2019, pp. 3982–3992, doi: 10.18653/v1/D19-1410.
4. N. F. Liu, K. Lin, J. Hewitt, A. Paranjape, M. Bevilacqua, F. Petroni, and P. Liang, “Lost in the middle: How language models use long contexts,” Transactions of the Association for Computational Linguistics, vol. 12, pp. 157–173, 2024, doi: 10.1162/tacl_a_00638.
5. T. Yu et al., “Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task,” in Proc. 2018 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2018, pp. 3911–3921.
6. S. Yao et al., “ReAct: Synergizing reasoning and acting in language models,” in Proc. Int. Conf. Learning Representations (ICLR), 2023.
7. T. Schick et al., “Toolformer: Language models can teach themselves to use tools,” in Advances in Neural Information Processing Systems, vol. 36, 2023.
8. Y. Gao et al., “Retrieval-augmented generation for large language models: A survey,” arXiv:2312.10997, 2023.
9. S. Es, J. James, L. Espinosa-Anke, and S. Schockaert, “RAGAS: Automated evaluation of retrieval augmented generation,” in Proc. 18th Conf. European Chapter of the Association for Computational Linguistics: System Demonstrations, 2024, pp. 150–158, doi: 10.18653/v1/2024.eacl-demo.16.
10. Sujit Shibaprasad Maity, “StockBuddy: An interpretable and lightweight web-based decision support system for short-term equity forecasting and recommendation,” International Journal of Innovative Science and Research Technology, vol. 11, no. 3, pp. 1759–1769, Mar. 2026, doi: 10.38124/ijisrt/26mar1068. [Online]. Available: https://www.ijisrt.com/stockbuddy-an-interpretable-and-lightweight-webbased-decision-support-system-for-shortterm-equity-forecasting-and-recommendation.
11. Y. A. Malkov and D. A. Yashunin, “Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 4, pp. 824–836, 2020.
12. Y. Xu et al., “LayoutLM: Pre-training of text and layout for document image understanding,” in Proc. 26th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2020, pp. 1192–1200.
13. National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1, Jan. 2023, doi: 10.6028/NIST.AI.100-1.
14. National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile, NIST AI 600-1, July 2024, doi: 10.6028/NIST.AI.600-1.
15. OWASP Foundation, “LLM01: Prompt injection,” OWASP Top 10 for Large Language Model Applications. [Online]. Available: https://genai.owasp.org/llm-top-10/. Accessed: Oct. 10, 2026.
16. OWASP Foundation, “SQL injection prevention cheat sheet.” [Online]. Available: https://cheatsheetseries.owasp.org/cheatsheets/SQL_Injection_Prevention_Cheat_Sheet.html. Accessed: Oct. 10, 2026.
17. OWASP Foundation, “File upload cheat sheet.” [Online]. Available: https://cheatsheetseries.owasp.org/cheatsheets/File_Upload_Cheat_Sheet.html. Accessed: Oct. 10, 2026.
18. pgvector Contributors, “pgvector: Open-source vector similarity search for Postgres,” software repository. [Online]. Available: https://github.com/pgvector/pgvector. Accessed: Oct. 10, 2026.
19. M. Kleppmann, Designing Data-Intensive Applications: The Big Ideas Behind Reliable, Scalable, and Maintainable Systems. Sebastopol, CA, USA: O’Reilly Media, 2017.
20. National Institute of Standards and Technology, The NIST Cybersecurity Framework (CSF) 2.0, NIST CSWP 29, Feb. 2024, doi: 10.6028/NIST.CSWP.29.
21. Sujit Shibaprasad Maity, “An intelligent heart disease identification framework using supervised machine learning for clinical decision support,” International Journal for Multidisciplinary Research, vol. 8, no. 1, Jan.–Feb. 2026, doi: 10.36948/ijfmr.2026.v08i01.69115. [Online]. Available: https://www.ijfmr.com/research-paper.php?id=69115.