Adaptive Multimodal Document Ingestion and Self-Correcting Hybrid RAG via LangGraph Multi-Agent Workflow

Abstract

Document digitization and knowledge extraction remain challenging when dealing with heterogeneous PDF repositories comprising both machine-readable text and degraded, scanned visual artifacts. Traditional Optical Character Recognition (OCR) systems enforce rigid linear pipelines, while conventional Retrieval-Augmented Generation (RAG) models suffer from hallucination when context is sparse or noisy. In this paper, we propose DocuMind-AI, an end-to-end autonomous agentic architecture for document processing and intelligent question answering orchestrated via LangGraph. The framework introduces a dynamic routing agent that assesses character density metrics to intelligently dispatch inputs between fast native text extractors and multimodal vision large language models. Extracted text is normalized into structured Markdown through an automated cleansing agent and ingested into a dual-engine hybrid retrieval index combining BM25 lexical search with dense vector embeddings via Reciprocal Rank Fusion (RRF). Furthermore, a Corrective RAG (CRAG) self-reflection loop audits retrieved document chunks for semantic relevance, triggering automated query reformulation when retrieval confidence is low, and performs secondary hallucination auditing on synthesized answers. Empirical benchmarks demonstrate that our adaptive routing reduces multimodal API overhead by 68.4% on mixed corpora while achieving a 94.2% answer grounding accuracy, outperforming conventional single-engine RAG pipelines in both precision and computational efficiency. Keywords— Agentic AI; Optical Character Recognition; Corrective RAG; LangGraph; Multimodal LLM; Hybrid Search.