Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68520
Volume:
10 |
10 |
Oct 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Artificial Intelligence and Machine Learning
Zeal Polytechnic
Department of Artificial Intelligence and Machine Learning
Zeal Polytechnic
Department of Artificial Intelligence and Machine Learning
Zeal Polytechnic
Department of Artificial Intelligence and Machine Learning
Zeal Polytechnic
Department of Artificial Intelligence and Machine Learning
Zeal Polytechnic
Department of Artificial Intelligence and Machine Learning
Zeal Polytechnic
Retrieval-augmented generation (RAG) enables language models to answer enterprise questions using external documents; however semantic retrieval and multi-agent delegation create authorization risks when access checks occur only after search or answer generation. This study presents a literature-informed architecture for authorization-aware multi-agent RAG in which a policy decision point evaluates current user and resource attributes, whereas a policy enforcement point restricts the eligible candidate set before content reaches rerankers, agents, or a large language model. This design combines role-based and attribute-based access control, semantic embeddings, vector search, least-privilege delegation, provenance-aware auditing, and policy revalidation at protected access boundaries. A focused survey identifies risks including semantic overfetch, cross-domain synthesis leakage, stale permissions, and delegation escalation. The paper defines authorization-correctness conditions and proposes an evaluation protocol that compares authorization-first retrieval with a retrieve-then-filter baseline. The metrics include unauthorized-context exposure, authorized Recall@k, answer relevance, latency, revocation propagation time, delegation violations, and audit completeness. This study is a survey and design contribution; no benchmark results are claimed because the proposed prototype has not yet been empirically evaluated.
KEYWORDS
This paper presented a survey-informed architecture for authorization-aware multi-agent RAG. Its central requirement is to restrict the retrieval candidate set using current authorization decisions before content reaches rerankers, agents, or a language model. The design combines access-control policy, least-privilege delegation, provenance, and audit logging. Future work is to implement the prototype and measure security, relevance, and latency against a retrieve-then-filter baseline.
[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 Proc. Advances in Neural Information Processing Systems (NeurIPS), vol. 33, 2020, pp. 9459–9474. [2] N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using Siamese BERT-networks,” in Proc. EMNLP-IJCNLP, 2019, pp. 3982–3992, doi: 10.18653/v1/D19-1410. [3] R. Namboothiri, “SoK: Authorization in multi-agent retrieval-augmented generation systems,” preprint, Jan. 2026, doi: 10.5281/zenodo.18346863. [Online]. Available: https://rohithnamboothiri.com/research/sok-authorization-rag [4] R. Sandhu, D. Ferraiolo, and R. Kuhn, “The NIST model for role-based access control: Towards a unified standard,” in Proc. 5th ACM Workshop on Role-Based Access Control, 2000, pp. 47–63, doi: 10.1145/344287.344301. [5] V. C. Hu, D. Ferraiolo, R. Kuhn, A. Schnitzer, K. Sandlin, R. Miller, and K. Scarfone, Guide to Attribute Based Access Control (ABAC) Definition and Considerations, NIST Special Publication 800-162, updated Aug. 2019, doi: 10.6028/NIST.SP.800-162. [6] Qdrant, “Filtering,” Qdrant Documentation. [Online]. Available: https://qdrant.tech/documentation/search/filtering/. Accessed: Oct. 28, 2026. [7] OWASP Foundation, “OWASP Top 10 for Large Language Model Applications,” OWASP GenAI Security Project, 2025. [Online]. Available: https://genai.owasp.org/llm-top-10/.
Publication Date
10/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
4
Total views since publication
PDF Downloads
12
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...