Neural Graph Retrieval for Intelligent Enterprise Agents
DOI:
https://doi.org/10.5281/zenodo.21412117Keywords:
Graph-Enhanced RAG, Context-Aware LLMs, Enterprise AI Systems, Knowledge Graph Integration, Domain Ontologies, Agent-Centric Architectures, Neural Retrieval Optimization, Contextual Reasoning, Prompt Engineering, Tool-Augmented LLMs, Intelligent Service Agents, LLM Governance, AI Reliability, Retrieval Quality, Enterprise Chatbots, Question Answering Systems, Task-Centric Evaluation, AI Benchmarking, Customer Support Automation, AI Performance Optimization.Abstract
Graph-Enhanced Retrieval-Augmented Generation (Graph-RAG) and contextual architectures for large language models (LLMs) deliver performance, reliability, and governance for enterprise applications. Graph-enhanced RAG addresses neural retrieval deficiencies within enterprise chatbots, question-answering systems, and service automation agents. A contextually aware agent-centric architecture combines knowledge graphs, domain ontologies, and personal models to ensure contextual accuracy and suitability for the use case. In contrast to standard RAG augmentation, application-specific data and reasoning mechanisms are connected through prompt engineering, plugins, and external tools. Evaluation methodologies for context-aware agents include dedicated benchmark suites and task-centric quality metrics.
Enterprise deployments of RAG and large language models require performance, reliability, and governance. LLM generative capability is appealing for data indexing tasks like customer support chat interactions, service delivery, and knowledge management. However, the neural retrieval component of RAG suffers from novelty, specificity, and appropriateness issues that impact overall user experience. Scaling chatbots to handle repetitive queries created by less elaborate agents leads to a reduction in customer engagement. Operator confidence decreases further when these systems fail to escalate correctly when faced with complex problems.
References
1. Liu, J., Liu, J., Yang, Y., Wang, J., Wu, W., Zhao, D., & Yan, R. (2022). GNN-encoder: Learning a dual-encoder architecture via graph neural networks for dense passage retrieval. Findings of the Association for Computational Linguistics: EMNLP 2022, 564–575.
2. Wu, T., Bai, X., Guo, W., Liu, W., Li, S., & Yang, Y. (2023). Modeling fine-grained information via knowledge-aware hierarchical graph for zero-shot entity retrieval. Proceedings of the ACM International Conference on Web Search and Data Mining, 1021–1029.
3. Nagubandi, A. R. (2025). Advanced Predictive Autonomous Agents for Multiportfolio Risk Analytics and Real-Time Enterprise P&L Decisioning: Self-Learning AI Systems for Multi-counterparty Derivatives, Collateral Valuation, and Accounting Reconciliation. Collateral Valuation, and Accounting Reconciliation (December 01, 2025).
4. Wang, D., Liu, S., Wang, H., Grau, B. C., Song, L., Tang, J., & Liu, Q. (2023). An empirical study of retrieval-enhanced graph neural networks. Frontiers in Artificial Intelligence and Applications, 372, 2443–2450.
5. Mavromatis, C., & Karypis, G. (2024). GNN-RAG: Graph neural retrieval for large language model reasoning. arXiv preprint.
6. Mangalampalli, B. M., Bandi, V. D. V. K., Kolla, S. K., & Kumar, M. V. K. (2025). Towards Self-Evolving Healthcare Intelligence: Integrating Advanced Learning Systems with Real-Time Clinical Data Pipelines. Cultura: International Journal of Philosophy of Culture and Axiology, 22(12s), 464-486.
7. Zamiri, M., Qiang, Y., Nikolaev, F., Zhu, D., & Kotov, A. (2024). Benchmark and neural architecture for conversational entity retrieval from a knowledge graph. Proceedings of the ACM Web Conference, 1519–1528.
8. Edge, D., et al. (2024). From local to global: A graph RAG approach to query-focused summarization. arXiv preprint.
9. Mialon, G., et al. (2023). Augmented language models: A survey. Transactions on Machine Learning Research, 1–45.
10. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Wang, Y., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint.
11. Lewis, P., et al. (2022). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 35, 9459–9474.
12. Mangalampalli, B. M., Bandi, V. D. V. K., Kolla, S. K., & Kumar, M. V. K. (2025). Towards Self-Evolving Healthcare Intelligence: Integrating Advanced Learning Systems with Real-Time Clinical Data Pipelines. Cultura: International Journal of Philosophy of Culture and Axiology, 22(12s), 464-486.
13. Yasunaga, M., et al. (2022). QA-GNN: Reasoning with language models and knowledge graphs for question answering. Proceedings of NAACL-HLT, 535–546.
14. Seenu, A., Aitha, A. R., Gottimukkala, V. R. R., Singireddy, J., Meda, R., & Garapati, R. S. (2025, November). Hybrid Multi-Agent Reinforcement Learning and Blockchain Framework for Real-Time Transaction Integrity in Cloud-Driven Financial Systems. In 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN) (pp. 1-6). IEEE.
15. Sun, H., et al. (2022). Think-on-graph: Deep and responsible reasoning of large language models with knowledge graphs. arXiv preprint.
16. Jiang, J., et al. (2023). Graph neural retrieval for multi-hop reasoning. Proceedings of AAAI, 37(4), 4451–4460.
17. Zhu, X., et al. (2023). Knowledge graph enhanced retrieval for enterprise AI systems. Information Processing & Management, 60(4), 103356.
18. Kolla, T. (2025). Generative AI for Intelligent Medical Coding and Healthcare Analytics. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 8(6), 13285-13299.
19. Chen, W., et al. (2024). Graph retrieval augmented generation for enterprise knowledge systems. ACM Transactions on Information Systems, 42(3), 1–29.
20. Li, Y., et al. (2024). Dynamic graph memory networks for intelligent enterprise agents. IEEE Transactions on Neural Networks and Learning Systems, 35(6), 7890–7904.
21. Kurenkov, A., et al. (2023). Modeling dynamic environments with scene graph memory. Advances in Neural Information Processing Systems, 36, 21034–21049.
22. AGENTIC AI FRAMEWORKS FOR AUTONOMOUS RISK DETECTION AND COMPLIANCE REMEDIATION IN ENTERPRISE DATA CENTER OPERATIONS. (2025). Lex Localis - Journal of Local Self-Government, 23(S6), 9672-9697. https://doi.org/10.52152/3f90ak91
23. Pan, S., et al. (2022). Graph learning for intelligent systems: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7543–7567.
24. Zhang, X., et al. (2022). Knowledge-aware graph retrieval in conversational agents. Proceedings of COLING, 2301–2313.
25. He, K., et al. (2023). Multi-hop graph retrieval with transformer-enhanced graph attention. Proceedings of ACL, 4511–4524.
26. Xu, L., et al. (2023). Graph-based memory augmentation for large language models. arXiv preprint.
27. Yu, S., et al. (2024). Enterprise graph intelligence for autonomous AI agents. IEEE Access, 12, 44821–44839.
28. Kolla, S. K., & Bandi, V. D. V. K. (2025). Autonomous Clinical Monitoring Platforms Using Reinforcement Learning and Deep Neural Networks. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 8(6), 13300-13313.
29. Yang, H., et al. (2024). Hybrid vector and graph retrieval for enterprise search. Information Sciences, 671, 119870.
30. Mangala, N., & Kolla, S. H. (2025). Real-Time Feature Engineering for Streaming AI Workloads Using PySpark and Azure Event Hubs. International Journal of Multidisciplinary Research in Science, Engineering, Technology & Management, 1(6), 93-105.
31. Cao, R., et al. (2022). Graph reasoning networks for knowledge-intensive retrieval. Proceedings of IJCAI, 3456–3464.
32. Zhou, D., et al. (2023). Retrieval-enhanced graph transformers for intelligent systems. Pattern Recognition, 142, 109641.
33. Guo, J., et al. (2024). Knowledge graph retrieval augmented generation in enterprise workflows. Future Generation Computer Systems, 154, 122–138.
34. Park, J., et al. (2025). Graphiti: Dynamic knowledge graphs for enterprise AI memory. arXiv preprint.
35. Kolla, S. H., & Peddi, R. K. (2024). Designing Governance-Aligned GenAI Pipelines Using Small Language Models for Enterprise Workflow Intelligence. International Journal of Science, Research and Technology, 7(6), 13256-13268.
36. Rasmussen, P., Paliychuk, P., Beauvais, T., Ryan, J., & Chalef, D. (2025). Zep: A temporal knowledge graph architecture for agent memory. arXiv preprint.
37. Li, T., et al. (2025). Neural graph memory for intelligent enterprise automation. Expert Systems with Applications, 245, 122344.
38. Mangala, N., & Kolla, S. H. (2025). Real-Time Feature Engineering for Streaming AI Workloads Using PySpark and Azure Event Hubs. International Journal of Multidisciplinary Research in Science, Engineering, Technology & Management, 1(6), 93-105.
39. Zhao, Q., et al. (2022). Graph neural networks for retrieval and reasoning: A survey. ACM Computing Surveys, 55(7), 1–36.
40. Kumar, V., et al. (2024). Knowledge graph-guided RAG for financial enterprise intelligence. IEEE Access, 12, 67432–67448.
41. Singh, A., et al. (2023). Neural subgraph retrieval for intelligent assistants. Proceedings of EMNLP, 9872–9885.
42. Babaiah, C., Dobriyal, N., Shamila, M., Aitha, A. R., Patel, S. P., & Upodhyay, D. (2025, December). Intelligent Fault Detection and Recovery in Wireless Sensor Networks Using AI. In 2025 IEEE 5th International Conference on ICT in Business Industry & Government (ICTBIG) (pp. 1-6). IEEE.
43. Patel, M., et al. (2024). Intelligent graph retrieval for enterprise decision systems. Decision Support Systems, 180, 114198.
44. Huang, Z., et al. (2023). Graph-based semantic retrieval for large-scale enterprise agents. Knowledge-Based Systems, 277, 110855.
45. Nagabhyru, K. C., & Kumar, M. V. K. (2025). Generative AI Meets Data Engineering: Automating Code, Query Generation, And Data Insights in Large Scale Enterprises. Query Generation, And Data Insights in Large Scale Enterprises (April 23, 2025).
46. Chen, Y., et al. (2022). Learning graph representations for dense retrieval. Proceedings of SIGIR, 1550–1560.
47. Luo, X., et al. (2024). Graph-augmented retrieval for enterprise AI governance. Information Systems Frontiers, 26(3), 721–739.
48. Wang, Y., et al. (2025). Enterprise graph memory and retrieval for autonomous agents. Journal of Systems Architecture, 152, 103219.
49. Kolla, S. H., & Mattaparthi, R. (2025). Hybrid Gen AI Systems: Integrating Small LMs with Large Language Models for Cost-Efficient Enterprise Automation and Decision Intelligence. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(6), 13345-13357.
50. Lin, H., et al. (2023). Multi-relational graph retrieval in knowledge-intensive systems. Proceedings of KDD, 2410–2422.
51. Zhao, P., et al. (2022). Neural graph search for question answering. Artificial Intelligence, 311, 103751.
52. Shen, L., et al. (2024). Intelligent graph retrieval pipelines for LLM agents. IEEE Intelligent Systems, 39(4), 33–46.
53. Segireddy, A. R. (2025). AN INTELLIGENT, REAL-TIME DIGITAL FABRIC FOR HEALTHCARE AND FINANCIAL ECOSYSTEMS USING AUTONOMOUS LEARNING AND GENERATIVE SYSTEMS. TPM–Testing, Psychometrics, Methodology in Applied Psychology.
54. Gupta, S., et al. (2025). Adaptive graph retrieval architectures for enterprise-scale agents. ACM Transactions on Knowledge Discovery from Data, 19(1), 1–25.
55. Brown, T., et al. (2022). Knowledge graph retrieval in enterprise automation. Journal of Information Technology, 37(4), 411–427.
56. Feng, J., et al. (2023). Graph memory reasoning for autonomous enterprise agents. Neural Networks, 164, 189–205.
57. Davuluri, P. N. (2020). Improving Data Quality and Lineage in Regulated Financial Data Platforms. Finance and Economics, 1(1), 1-14.
58. Mehta, R., et al. (2024). Graph-centric retrieval augmentation for regulated enterprise AI. Expert Systems, 41(6), e13301.
59. Das, A., et al. (2022). Learning efficient subgraph retrieval representations. Proceedings of WWW, 1221–1233.
60. Verma, P., et al. (2023). Context-aware graph retrieval for intelligent business systems. IEEE Transactions on Knowledge and Data Engineering, 35(9), 9110–9125.
61. Roy, K., et al. (2024). Enterprise-scale graph retrieval for financial AI ecosystems. Journal of Financial Data Science, 6(2), 88–103.
62. Garapati, R. S. (2025). Real-Time Monitoring and AI-Based Control of Industrial Robots Using Cloud-Hosted Web Applications. Available at SSRN 5612491.
63. Banerjee, D., et al. (2025). Autonomous graph retrieval agents for knowledge-driven enterprises. AI Magazine, 46(1), 56–71.
64. Khandelwal, U., et al. (2022). Retrieval memory for transformer agents. Transactions of the ACL, 10, 973–988.
65. Hu, M., et al. (2024). GraphRAG for intelligent document reasoning. Proceedings of ACL, 6220–6236.
66. Ren, Y., et al. (2025). Neural graph orchestration for multi-agent enterprise intelligence. IEEE Transactions on Services Computing, 18(2), 994–1009.
67. Singh, V., et al. (2023). Graph-enhanced retrieval for enterprise knowledge management. Knowledge and Information Systems, 65(8), 3191–3210.
68. Reddy, V. A. R. (2025). Journal of Rare Cardiovascular Diseases. Health, 5(3), 402-422.
69. Gao, T., et al. (2024). Graph retrieval pipelines for enterprise compliance automation. Information & Management, 61(5), 104011.
70. Zhao, H., et al. (2022). Knowledge-intensive graph search with neural retrievers. Proceedings of AAAI, 36(5), 5412–5420.
71. Kim, J., et al. (2023). Agentic retrieval systems with graph reasoning layers. Proceedings of IJCAI, 4177–4185.
72. Das, N., Qubeb, S. M. P., Amistapuram, K., & Yadav, R. K. (2025). Artificial Inteligence and Data Science. BR Publications.
73. Lee, D., et al. (2024). Intelligent enterprise graph memory for contextual agents. Future Internet, 16(4), 121.
74. Xu, Z., et al. (2025). Self-evolving graph retrieval architectures for enterprise intelligence. IEEE Transactions on Big Data, 11(1), 221–237.
75. Thomas, E., et al. (2023). Knowledge graph retrieval for autonomous service agents. Journal of Web Semantics, 79, 100801.
76. Green, M., et al. (2024). Large language models with graph retrieval memory. Machine Learning with Applications, 18, 100612.
77. Pamisetty, A., Paleti, S., Adusupalli, B., Singireddy, J., Inala, R., & Nagabhyru, K. C. (2025, September). Explainable AI Systems for Credit Scoring and Loan Risk Assessment in Digital Banking Platforms. In 2025 IEEE 13th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) (pp. 1478-1483). IEEE.
78. Kapoor, N., et al. (2025). Enterprise-grade graph retrieval augmented reasoning systems. Expert Systems with Applications, 252, 123445.
79. Bansal, S., Sistla, S. S., Arikatala, A., & Schreiber, S. (2025). Planning agents on an ego-trip: Leveraging hybrid ego-graph ensembles for improved tool retrieval in enterprise task planning. arXiv preprint.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2025 Mallesham Goli (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons
Attribution 4.0 International License (CC BY 4.0).
You are free to:
- Share: copy and redistribute the material
- Adapt: remix, transform, and build upon the material
for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit to
the original author(s) and source.
Full license text: https://creativecommons.org/licenses/by/4.0/
