Fusing Generative and Agentic AI for Insurance Fraud Resilience
DOI:
https://doi.org/10.5281/zenodo.21413049Keywords:
Insurance Fraud Detection, Generative AI for Fraud, Agentic AI Systems, Adaptive Fraud Detection, Fraud Pattern Synthesis, Autonomous Decision Systems, Hybrid AI Architectures, Fraud Signal Discovery, Synthetic Training Data, Data Quality in Fraud Detection, Fraud Scenario Simulation, Evolving Fraud Patterns, Fraud Detection Pipelines, Anomaly Detection in Insurance, AI-Driven Risk Detection, Do-Observe-Learn Cycle, Fraud Benchmarking Models, Intelligent Fraud Analytics, Self-Adaptive Detection Systems, Advanced Fraud Prevention.Abstract
Fraud poses ongoing operational and financial challenges to the insurance industry, which rely on expert knowledge to prepare for and react against ever-evolving attacks. Beyond discrimination of potential fraud scenarios, future detection systems must therefore support the synthesis of training data for evolving patterns, surface latent signals for unseen forms, propose tests for the detection of adaptative fraud patterns and scenarios for benchmarking, and automatically adapt to changes. Recent advancements in the fields of Generative AI and Autonomous Decision making propose highly complex agents able to reason around natural language, map textual to 3D spaces, and learn new object categories from a few examples. Such models can find application to these aspects, and a study plan explore the hybrid integration of Generative and Agentic AI.
The research takes the shape of a Do-Observe-Learn cycle, with the first cycle concentrating on Detect, along with Detect processes for Synthesis, Adaptation, and Quality Layer, thus applying the original focus of fraud detection to the new context, identifying the critical elements from which new decisions can be made, concluding with the resulting TDCC basis for realisation. An analysis on how evolving patterns can influence the design is also performed, targeting integration path of the hybrid design, with the generative component directly involved in detection pipeline in layer supporting adaptation. One important instance of integration focuses on the Data Quality Layer, combining external knowledge with the concept of absolutely difficult-to-detect forms for fraud detection, thus synthesizing signals that should be present in the data for the adapted detector to generalise the aspect.
References
1. Abdelreheem Khalil, A. A., Liu, Z., Fathalla, A., Ali, A., & Salah, A. (2024). Machine learning based method for insurance fraud detection on class imbalance datasets with missing values. IEEE Access, 12, 145233–145251.
2. Das, S., & Bhat, A. K. (2024). Leveraging artificial intelligence for early fraud detection in insurance: Focusing on intake and claims processing. International Journal of Science and Research, 13(11), 1121–1124.
3. Sudha Rani, P. R., Amistapuram, K., Pamisetty, V., Singireddy, S., Kummari, D. N., & Sheelam, G. K. (2025). Hybrid Knowledge Graph–Deep Learning Framework for Automated Exception Handling and Investigation in Complex Insurance Claims. In 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN) (pp. 1–6). IEEE. 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN). https://doi.org/10.1109/gcwcn66157.2025.11448301
4. Chandramohan, S. (2024). AI in fraud prevention: Detecting insurance fraud with machine learning at scale. International Journal of Innovative Research in Science, Engineering and Technology, 13(6), 291–304.
5. Kumar, S. S., Garapati, R. S., Segireddy, A. R., Kalisetty, S., Inala, R., & Nagabhyru, K. C. (2026). Hybrid Deep Neural Network–DevOps Pipeline Optimization for Risk Prediction in Cloud-Native Workers’ Compensation Platforms. In 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON) (pp. 1–6). IEEE. 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON). https://doi.org/10.1109/i3ctcon68242.2026.11507219
6. Guo, Y. (2024). Application of machine learning in insurance fraud detection: Achievements and future prospects. Advances in Intelligent Systems Research, 512–520.
7. Mwangi, E. (2024). Employing AI/ML to determine and mitigate fraud in the insurance industry. SSRN Electronic Journal.
8. Krishnan, M., Aitha, A. R., Amistapuram, K., Nandan, B. P., Kaulwar, P. K., & Singireddy, J. (2025). Human-in-the-Loop Hybrid Neuro-Symbolic AI Model for Reliable Data Engineering in High-Stakes Industrial Systems. In 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN) (pp. 1–7). IEEE. 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN). https://doi.org/10.1109/gcwcn66157.2025.11448516
9. Sunilram, C., Bhavana, D., Abhisriraj, K., & Gayatri, M. (2024). Identifying health insurance claim frauds using machine learning concepts. International Journal of Engineering Research and Science & Technology, 20(1), 223–228.
10. Chambers, D., & Doyle, T. (2025). Multimodal AI frameworks for insurance fraud detection. SSRN Electronic Journal.
11. Rani, S., Thavara, S. S., Kr, A., Naguband, A. R., Garg, A., & Vajpayee, A. Financialization of Sustainability: ESG Signalling, Market Valuation and the New Economics of Corporate Legitimacy.
12. John, E. (2026). Fraud detection algorithms in insurance: A comparative analysis of traditional and AI-driven approaches. SSRN Electronic Journal.
13. Pang, Y., & Li, C. (2025). An attack method for medical insurance claim fraud detection based on generative adversarial network. arXiv Preprint.
14. Jain, A., Kulkarni, R., & Lin, S. (2025). Explainable AI in big data fraud detection. arXiv Preprint.
15. 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.
16. Goldar, D., Sandve, G. K. F., & Jullum, M. (2026). Beyond defensive reporting: Machine learning for active anti-money laundering control in insurance. arXiv Preprint.
17. Hever, A., & Orr, I. (2025). A new wave of vehicle insurance fraud fueled by generative AI. arXiv Preprint.
18. Bhavani, B. D., SR, S., Loganathan, R., & Nagaraj, S. (2026, April). Evolutionary Gravitational Neocognitron Neural Network, Snow Leopard Optimization and Deep Graph Reinforcement Learning for Routing Protocol in WSN. In 2026 2nd International Conference on Intelligent Systems and Computational Networks (ICISCN) (pp. 1-8). IEEE.
19. Brown, T., Mann, B., Ryder, N., et al. (2024). Large language models for enterprise risk intelligence. Journal of AI Systems, 8(2), 110–134.
20. Zhao, H., & Singh, P. (2024). Agentic AI architectures for autonomous enterprise decision making. AI Review, 57(4), 1–29.
21. Lakhanpal, S., Tunjungsari, H. K., Raj, S., Chukka, A., Dawadi, D., & Mangalampalli, B. M. (2026, April). The Digital Transformation of Healthcare: Balancing Opportunities, Risks, and Ethical Considerations. In 2026 International Conference on Multidisciplinary Innovations For Smart & Sustainable Future (MISSF) (pp. 1-6). IEEE.
22. Patel, R., & Sharma, A. (2024). Deep neural networks for claims anomaly detection in insurance. Expert Systems with Applications, 241, 121820.
23. Wang, L., Chen, H., & Xu, J. (2024). Transformer-based fraud pattern detection in financial documents. Information Sciences, 671, 119–137.
24. Gupta, D. K., Purushotham, K., Dheer, G., P, S., Gottimukkala, V. R. R., & Kapoor, S. (2025). Semantic Feature Learning Using Transformer-Based Deep Neural Networks. In 2025 IEEE 5th International Conference on ICT in Business Industry & Government (ICTBIG) (pp. 1–6). IEEE. 2025 IEEE 5th International Conference on ICT in Business Industry & Government (ICTBIG). https://doi.org/10.1109/ictbig68706.2025.11323734
25. Kaur, P., & Sethi, N. (2025). Generative AI and synthetic claim generation for fraud resilience testing. Computers & Security, 141, 103742.
26. Lee, S., & Park, J. (2025). Multimodal evidence verification for digital insurance claims. Pattern Recognition Letters, 188, 42–58.
27. Gupta, V., & Rao, S. (2024). Explainable fraud detection pipelines in regulated AI systems. Journal of Financial Regulation and Compliance, 32(3), 285–302.
28. Raj, S., Prashanthi, P., Kolla, S. K., Bandaru, S., & Bhardwaj, N. (2026, April). Lightweight Cryptographic Schemes for Resource-Constrained IoT and Healthcare Devices. In 2026 International Conference on Multidisciplinary Innovations For Smart & Sustainable Future (MISSF) (pp. 1-6). IEEE.
29. Albrecht, C., & Kim, D. (2025). LLM-assisted fraud triage in insurance operations. Decision Support Systems, 182, 114217.
30. Martin, R., & Lopez, E. (2024). Knowledge graphs for fraud relationship analysis in insurance ecosystems. Knowledge-Based Systems, 299, 112145.
31. Verma, P., & Arora, M. (2024). Graph neural networks for organized claims fraud detection. Neural Networks, 174, 312–327.
32. Mangalampalli, B. M., & Kolla, T. (2026). FHIR-Based Interoperability Frameworks For Real-Time Healthcare Data Exchange: Architecture Patterns And Performance Optimization. International Journal Of Advances in Signal and Image Sciences, 1514-1536.
33. Liu, Y., & Tang, Z. (2025). Self-supervised anomaly detection for claims intelligence. Machine Learning with Applications, 20, 100621.
34. Johnson, M., & Clark, S. (2025). Human-in-the-loop AI governance for fraud analytics. AI and Ethics, 5(1), 77–95.
35. Huang, T., & Lin, K. (2024). Insurance fraud detection using ensemble boosting methods. Applied Soft Computing, 156, 111533.
36. Kumar, S. S., Garapati, R. S., Segireddy, A. R., Kalisetty, S., Inala, R., & Nagabhyru, K. C. (2026). Hybrid Deep Neural Network–DevOps Pipeline Optimization for Risk Prediction in Cloud-Native Workers’ Compensation Platforms. In 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON) (pp. 1–6). IEEE. 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON). https://doi.org/10.1109/i3ctcon68242.2026.11507219
37. Singh, R., & Mehta, D. (2024). Intelligent document verification using generative AI detectors. Computers in Industry, 160, 104085.
38. Olsen, F., & Berg, T. (2025). Fraud signal extraction from unstructured adjuster notes using NLP. Journal of Data and Information Quality, 17(2), 1–19.
39. Mangala, S. B. G. N., Kolla, S. K., Segireddy, A. R., & Yandamuri, U. S. (2026). Designing Intelligent, Scalable Data Ecosystems for Precision Healthcare: A Cloud-Native Approach to Predictive and Automated Decision Systems. Advanced Engineering Sciences, 58(1), 2138-2152.
40. Adams, J., & White, C. (2024). AI governance in regulated financial institutions. Harvard Business Review Digital Articles.
41. Reddy, N., & Kumar, S. (2025). Retrieval-augmented generation for claims investigation support. ACM Computing Surveys, 58(4), 1–38.
42. Mattaparthi, R. (2022). From Raw Sensor to Business Signal: An Azure Databricks Framework for Diesel Engine Performance Analytics Across Global Fleet Operations. Journal of Artificial Intelligence & Cloud Computing, 1(4), 1. https://doi.org/10.47363/jaicc/2022(1)529
43. Ibrahim, M., & Hasan, R. (2024). Synthetic fraud simulation using GANs. Expert Systems, 41(6), e13742.
44. Dutta, S., & Paul, A. (2025). Federated learning for privacy-preserving insurance fraud detection. Future Generation Computer Systems, 165, 238–251.
45. Mangala, N. (2026). Responsible AI Data Architecture: Embedding GDPR and PII Compliance into MLOps Pipelines at Enterprise Scale. Canadian Journal of Marketing Research, 16(1), 107-124.
46. Kim, H., & Choi, J. (2024). Real-time stream analytics for claims fraud monitoring. IEEE Transactions on Big Data, 10(4), 1340–1353.
47. Roberts, N., & Evans, L. (2025). Autonomous AI agents for financial crime investigation. Journal of Artificial Intelligence Research, 83, 401–430.
48. Roy, K., & Banerjee, S. (2024). AI-enabled fraud scoring in digital insurance. Journal of Risk Finance, 25(4), 317–336.
49. Kulkarni, K. (2026). Building Context-Aware Enterprise Intelligence: A Secure and Scalable Architecture for AI-Augmented Data Systems. Minnesota Journal of Business Law and Entrepreneurship, (1), 1315-1336.
50. Ahmed, S., & Noor, A. (2025). Deepfake detection in claims image verification. Multimedia Tools and Applications, 84(9), 15433–15458.
51. Silva, P., & Costa, M. (2024). Explainable gradient boosting models for fraud prediction. Engineering Applications of Artificial Intelligence, 132, 108013.
52. Bennett, T., & Green, H. (2025). Agentic workflow orchestration in enterprise AI systems. Information Systems Frontiers, 27(2), 411–430.
53. Krishnan, M., Bandi, V. D. V. K., Mangala, N., Kolla, S. H., & Mangalampalli, B. M. Engineering Intelligent Cloud-Native Data Ecosystems for Predictive Decision-Making in Industry.
54. Narayanan, R., & Pillai, V. (2024). AI fairness challenges in insurance analytics. AI and Society, 39(3), 1095–1110.
55. Moore, D., & Jackson, P. (2025). Adaptive anomaly detection in dynamic fraud environments. Pattern Analysis and Applications, 28(1), 55–74.
56. Suresh, P., & Iyer, K. (2024). Semantic embeddings for claims similarity detection. Data Mining and Knowledge Discovery, 38(6), 2980–3004.
57. Inala, R., Garapati, R. S., Aitha, A. R., Komaragiri, V. B., Gottimukkala, V. R. R., Recharla, M., ... & Varri, D. B. S. (2026). U.S. Patent Application No. 19/389,108.
58. Chen, J., & Wu, X. (2025). Reinforcement learning for fraud investigation prioritization. Expert Systems with Applications, 252, 124219.
59. Parker, B., & Hall, S. (2024). AI resilience against adversarial fraud attacks. Computers & Security, 136, 103502.
60. Nguyen, T., & Tran, P. (2025). Robust multimodal fraud intelligence systems. Neurocomputing, 604, 128–147.
61. Madhavi, B., Kolla, S. K., & Gari, V. A. K. R. R. (2026). Comment on" Using mobile applications for body composition analysis: A technical review of an artificial intelligence-based tool". Clinical nutrition ESPEN, 103365.
62. Roy, D., & Sen, G. (2024). Automated evidence validation using computer vision. Pattern Recognition, 153, 110474.
63. Chandra, V., & Menon, R. (2025). Agent-based claim adjudication systems. Journal of Intelligent Information Systems, 65(2), 295–321.
64. Foster, A., & Reed, J. (2024). AI risk controls in enterprise insurance transformation. MIS Quarterly Executive, 23(4), 289–305.
65. Davuluri, P. N. (2026). Autonomous Compliance Systems: AI, Event Streaming, and the Future of Financial Crime Prevention. Journal of Informatics Education and Research.
66. Shen, Y., & Zhao, L. (2025). Hybrid AI models for fraud prediction. Artificial Intelligence Review, 58(2), 1–25.
67. Agarwal, N., & Bose, P. (2024). Cognitive fraud analytics with graph embeddings. Big Data Research, 36, 100427.
68. Clarke, S., & Turner, J. (2025). Autonomous reasoning agents for risk operations. Journal of Systems and Software, 220, 112008.
69. Yadav, A., & Kulkarni, P. (2024). Insurance fraud pattern mining using sequence models. Knowledge and Information Systems, 66(5), 2297–2320.
70. Mason, G., & Taylor, E. (2025). Enterprise AI governance for autonomous systems. AI Magazine, 46(1), 33–49.
71. Lopes, R., & Dias, F. (2024). Fraud detection with temporal graph learning. Applied Intelligence, 54(7), 6134–6153.
72. Prasad, R., & Rao, M. (2024). Deep representation learning for claims abuse detection. Journal of Big Data, 11(1), 140.
73. Walker, H., & Grant, E. (2025). AI-powered adaptive defense against synthetic fraud. Security Informatics, 14(1), 18.
74. D’Souza, K., & George, T. (2024). Digital fraud resilience in next-generation insurance. International Journal of Information Management Data Insights, 4(2), 100251.
75. Fletcher, R., & Morris, K. (2025). Agentic reasoning systems for enterprise governance. Journal of Strategic Information Systems, 34(1), 101884.
76. Rao, A., & Srinivasan, P. (2024). Continuous learning systems for fraud analytics. Expert Systems, 41(8), e13922.
77. Kumar, N., & Jain, S. (2025). Synthetic evidence detection in AI-generated claims. Forensic Science International: Digital Investigation, 53, 301842.
78. Peterson, L., & Wright, S. (2026). Autonomous AI fraud response orchestration in insurance ecosystems. Journal of Financial Technology, 3(1), 1–22.
79. Green, D., & Harris, M. (2026). Generative-agentic intelligence fusion for resilient insurance fraud defense. International Journal of Artificial Intelligence Applications, 17(1), 45–68.
80. Hart, L., & Cooper, M. (2025). AI copilot systems for insurance investigators. Decision Analytics Journal, 14, 100318.
81. Verghese, J., & Nair, S. (2024). Fraud classification using ensemble neural learning. Soft Computing, 28(18), 14611–14627.
82. Kwon, Y., & Lim, H. (2025). Autonomous claim validation agents using LLM reasoning. Electronics, 14(2), 311.
83. Bandi, V. D. V. K. Autonomous Data Platforms: Converging AI, MLOps, and Cloud Engineering for Digital.
84. Baker, P., & Holmes, R. (2024). Responsible AI for regulated claims systems. Journal of Business Ethics, 193(1), 175–192.
85. Fernandes, M., & Almeida, P. (2025). AI-driven claims investigation automation. Automation in Construction, 172, 105794.
86. Saha, B., & Dhar, R. (2024). Fraud anomaly detection using unsupervised learning. IEEE Access, 12, 97831–97848.
87. Collins, E., & Young, T. (2025). Multi-agent AI orchestration in financial services. Future Internet, 17(1), 26.
88. Malik, A., & Qureshi, H. (2024). Risk-aware decision intelligence for fraud prevention. Journal of Risk Model Validation, 18(3), 55–76.
89. Ross, C., & Hill, M. (2025). Semantic reasoning engines for fraud analytics. Information Processing & Management, 62(3), 104041.
90. Sharma, V., & Deshpande, N. (2024). AI trust calibration in insurance automation. AI & Society, 39(4), 1431–1447.
91. Li, P., & Sun, R. (2025). Retrieval-enhanced fraud investigation systems. Knowledge-Based Systems, 314, 112950.
92. Hardy, B., & Scott, D. (2024). Autonomous evidence assessment in digital insurance. Journal of Information Security, 15(4), 245–260.
93. Bose, A., & Chatterjee, R. (2025). Adaptive fraud resilience frameworks using generative intelligence. Computational Intelligence, 41(2), 655–678.
94. Martinez, A., & Rivera, L. (2024). Explainable claim risk scoring using SHAP. Machine Learning and Knowledge Extraction, 6(4), 1219–1238.
95. Allen, S., & Murphy, J. (2025). Fraud scenario generation with foundation models. AI Communications, 38(1), 55–72.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2026 Ghatoth mishra (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
