Agentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World Applications
This addresses a critical gap in knowledge-intensive domains like scientific research, though it appears incremental as an application of existing agentic RAG concepts to a specific domain.
The paper tackles the problem of conventional RAG systems delivering limited answers on complex queries by introducing INRAExplorer, an agentic RAG system that uses a knowledge graph from INRAE publications to perform multi-hop reasoning and deliver structured answers.
Conventional Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) but often fall short on complex queries, delivering limited, extractive answers and struggling with multiple targeted retrievals or navigating intricate entity relationships. This is a critical gap in knowledge-intensive domains. We introduce INRAExplorer, an agentic RAG system for exploring the scientific data of INRAE (France's National Research Institute for Agriculture, Food and Environment). INRAExplorer employs an LLM-based agent with a multi-tool architecture to dynamically engage a rich knowledge base, through a comprehensive knowledge graph derived from open access INRAE publications. This design empowers INRAExplorer to conduct iterative, targeted queries, retrieve exhaustive datasets (e.g., all publications by an author), perform multi-hop reasoning, and deliver structured, comprehensive answers. INRAExplorer serves as a concrete illustration of enhancing knowledge interaction in specialized fields.