Agentic AI with RAG and Knowledge Graphs: A Novel Framework for Transforming Enterprise E-Commerce Operations

DOI

10.2991/978-94-6463-978-0_20How to use a DOI?

Keywords

Agentic AI; Retrieval-Augmented Generation; Knowledge Graphs; Enterprise E-Commerce; Multi-Agent Systems; Graph Neural Networks

Abstract

The synthesis of Agentic AI, Retrieval-Augmented Generation (RAG), and Knowledge Graphs, is a paradigm shift in e-commerce systems of enterprises. The current paper suggests KG-RAG-Agent, a new framework that is based on the combination of autonomous AI agents with graph-enhanced retrieval methods and organized knowledge representation. We propose the Adaptive Multi-Hop Retrieval Algorithm (AMHRA), which dynamically ensure the optimization of the retrieval paths with the use of knowledge graphs depending on the complexity of queries and context. Theoretic limits on accuracy and complexity of retrieval are determined by our mathematical model. The outcomes of the experiment indicate that the accuracy of the query resolution, operational costs and customer satisfaction metrics are increased by 58.3, 42.7, and 31.5, respectively, in comparison with baseline systems. The framework has single-hop retrieval complexity that is O(log n) and khop reasoning complexity of O(k log n) with n and k being knowledge graph size. Extensive assessment of 5 enterprise use cases confirms the efficacy of our methodology in the processes of real-world use.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shylaja Chityala
AU  - N. V. Madhu Bindu
PY  - 2025
DA  - 2025/12/31
TI  - Agentic AI with RAG and Knowledge Graphs: A Novel Framework for Transforming Enterprise E-Commerce Operations
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 223
EP  - 229
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_20
DO  - 10.2991/978-94-6463-978-0_20
ID  - Chityala2025
ER  -