Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186174,
        author = {Aryan Mullick and Prasad Kakulate and Tanay Prabhu and Shlok Salgaonkar},
        title = {Agentic AI-Based Document Intelligence System: A Multi-Agent Framework for Document based Localized Assistant using Multi-Agent Retrieval - DocLAMAR},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {716-720},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186174},
        abstract = {The growing complexity of unstructured digital data has intensified the demand for intelligent systems that can efficiently retrieve and summarize information from local repositories. Conventional search mechanisms rely heavily on keyword-based retrieval, lacking semantic comprehension and contextual accuracy. Recent advancements in multi-Agent frameworks and Retrieval-Augmented Generation (RAG) models have shown potential in overcoming these limitations by enabling collaborative and context-aware information processing. This paper presents a review of a Document-Based Localized Assistant that leverages a multi-agent architecture integrating Routing, Parsing, Re-Ranking, and Summarizing agents. The system employs Large Language Models (LLMs) within a CrewAI-based workflow to autonomously extract, analyze, and condense document information while maintaining user data confidentiality through localized execution. By combining modular agent interaction with natural language understanding, the framework achieves improved retrieval precision, reduced latency, and enhanced interpretability. The proposed approach demonstrates applicability in domains such as legal, corporate, and healthcare sectors where efficient and private document analysis is crucial.},
        keywords = {Agentic AI, Multi-Agent Systems, Retrieval-Augmented	Generation,	Document Summarization, CrewAI, Localized Search, Large Language Models.},
        month = {November},
        }