Graph-Augmented AI Systems for Deep Reasoning in Enterprise Codebases and Regulatory Documents

DOI

10.2991/978-94-6239-654-8_56How to use a DOI?

Keywords

Graph-Augmented AI; Deep reasoning; enterprise codebases; regulatory documents; graphRAG; knowledge graph-based reasoning; dependency tracing

Abstract

Enterprise-scale codebases and regulatory documents require deep reasoning capabilities to handle the associated issue of complexity, semantic diversity, and compliance requirements. We propose graph-agumanted AI system for deep reasoning, focused on enabling graph-augmented deep reasoning through a novel algorithm, GraphRAG, with knowledge graph-based reasoning, which integrates retrieval-augmented generation with structured knowledge graphs. This yield accuracy as high as 91%, outperforming transformer-only baselines across applications like dependency tracing, compliance validation, and semantic query resolution. By embedding graph augmentation, we enable improved contextual grounding, relational inference, and interpretability, all essential features to ensure scalability and transparency in mission-critical enterprise environments. The future work including generalizing this framework to multimodal enterprise assets, enabling dynamic evolution of the graph for real-time updates, and embedding ethics and human-centric principles to ensure responsible innovation in enterprise and regulatory intelligence.

Copyright

© 2026 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  - Kishore Subramanya Hebbar
AU  - Paras Patel
AU  - Shruthi Sepuri
PY  - 2026
DA  - 2026/04/24
TI  - Graph-Augmented AI Systems for Deep Reasoning in Enterprise Codebases and Regulatory Documents
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 708
EP  - 722
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_56
DO  - 10.2991/978-94-6239-654-8_56
ID  - Hebbar2026
ER  -