Chetanya Rathi

An Iterative Self-Correcting Agentic RAG System

2026 · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference

Traditional Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) with external knowledge but are limited by static, single-pass retrieval, making them less effective for complex, multi-step reasoning. This paper introduces a context-driven agentic RAG …