隨著銀行跨境營運規模擴大，海外分行在資訊安全與法令遵循作業上，需同時因應不同監理機關之規範要求，導致資安與法遵政策檢核流程面臨高度複雜與即時性挑戰。以紐約州金融服務署（New York State Department of Financial Services, NYDFS）Part 500 為例，其規範內容更新頻繁，現行以人工或規則式自動化為主的檢核作業，在效率與一致性上逐漸顯現限制。本研究以 T 銀行海外分行為研究對象，採用設計科學研究法，設計一套 Agentic AI 概念之資安與法遵政策檢核流程架構，透過多代理（Multi-Agent）協作方式，支援法規文件解析、條文比對與監理公告追蹤等作業需求。研究透過模擬法規修正情境與專家訪談進行驗證，結果顯示所提出之架構在法規差異辨識與檢核流程一致性方面，較傳統關鍵字檢索方式具備改善空間。研究亦指出，實務導入仍需搭配治理機制與人類參與流程，以確保檢核結果之可解釋性與可稽核性。

As banks expand cross-border operations, overseas branches must comply with regulatory requirements from multiple supervisory authorities, increasing the complexity and time sensitivity of cybersecurity and regulatory compliance review processes. The New York State Department of Financial Services (NYDFS) Part 500 is used as an example, as its requirements are updated frequently and existing review practices based on manual procedures or rule-based automation face limitations in efficiency and consistency. This study examines the overseas branches of T Bank and adopts the Design Science Research Methodology to design a compliance policy review framework based on the concept of Agentic AI. The framework applies a multi-agent approach to support regulatory document analysis, clause comparison, and regulatory announcement monitoring. The framework is evaluated through simulated regulatory amendment scenarios and expert interviews. The results indicate that the proposed framework improves the identification of regulatory differences and the consistency of review processes when compared with traditional keyword-based methods. The study also notes that practical implementation requires appropriate governance mechanisms and human-in-the-loop processes to support explainability and auditability.

Araci, D. (2019). FinBERT: Financial sentiment analysis with pre-trained language models. https://arxiv.org/abs/1908.10063
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. https://doi.org/10.1016/j.inffus.2019.12.012
Bandi, A., Kongari, B., Naguru, R., Pasnoor, S., & Vilipala, S. V. (2025). The rise of Agentic AI: A review of definitions, frameworks, architectures, applications, evaluation metrics, and challenges. Future Internet, 17(9), 404. https://doi.org/10.3390/fi17090404
Citigroup. (2025). Agentic AI: Finance & the ‘do it for me’ economy. Citi GPS: Global Perspectives & Solutions. https://www.citigroup.com/global/insights/citigps
Gregor, S., & Hevner, A. R. (2013). Positioning and Presenting Design Science Research for Maximum Impact1. MIS Quarterly, 37(2), 337–355. https://doi.org/10.25300/misq/2013/37.2.01
Gulli, A., Nigam, L., Wiesinger, J., Vuskovic, V., Sigler, I., Nardini, I., Stroppa, N., Kartakis, S., Saribekyan, N., Nawalgaria, A., & Bount, A. (2025, February). Agents companion (Technical report). Google.
He, J., Lin, H., Wang, Q., Fung, Y. R., & Ji, H. (2025). Self-correction is more than refinement: A learning framework for visual and language reasoning tasks. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 6405–6421). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.findings-acl.331
Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design Science in Information Systems Research1. MIS Quarterly, 28(1), 75–106. https://doi.org/10.2307/25148625
International Organization for Standardization & International Electrotechnical Commission. (2023). Information technology — Artificial intelligence — Management system (ISO/IEC 42001:2023). https://www.iso.org/standard/81230.html
Ji, Z., Yu, T., Xu, Y., Lee, N., Ishii, E., & Fung, P. (2023). Towards mitigating LLM hallucination via self-reflection. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 1827–1843). https://aclanthology.org/2023.findings-emnlp.123
Jurowetzki, R., & Squicciarini, M. (2025). Artificial intelligence and the evolution of AI (model) capabilities: A conceptual primer. United Nations Educational, Scientific and Cultural Organization.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020, May 22). Retrieval-Augmented Generation for Knowledge-Intensive NLP tasks. arXiv.org. https://arxiv.org/abs/2005.11401
Li, G., Hammoud, H. A. A. K., Itani, H., Khizbullin, D., & Ghanem, B. (2023). CAMEL: Communicative agents for mind exploration of large-scale language model society. arXiv. https://arxiv.org/abs/2303.17760
Monetary Authority of Singapore. (2021). Technology risk management guidelines (MAS 625). https://www.mas.gov.sg/regulation/guidelines/technology-risk-management-guidelines
New York State Department of Financial Services. (2023). Cybersecurity regulation (23 NYCRR Part 500). Retrieved January 23, 2026, from https://www.dfs.ny.gov/industry_guidance/cybersecurity
Nie, Y., Kong, Y., Dong, X., Mulvey, J. M., Poor, H. V., Wen, Q., & Zohren, S. (2024). A survey of large language models for financial applications: Progress, prospects and challenges. arXiv. https://arxiv.org/abs/2406.11903
NTT DATA Group Corporation. (2025). Intelligent banking in the age of AI: How GenAI will shape the future of payments, wealth management and fraud prevention. https://www.nttdata.com/global/en/insights
OWASP Foundation. (2023). OWASP Top 10 for large language model applications (version 1.1). https://owasp.org/www-project-top-10-for-large-language-model-applications/
Packer, C., Fang, V., Patil, S. G., Lin, K., Wooders, S., Stoica, I., & Gonzalez, J. E. (2023). MemGPT: Towards LLMs as operating systems. arXiv. https://arxiv.org/abs/2310.08560
Peffers, K., Tuunanen, T., Rothenberger, M. A., & Chatterjee, S. (2007). A Design Science Research Methodology for Information Systems Research. Journal of Management Information Systems, 24(3), 45–77. https://doi.org/10.2753/mis0742-1222240302
Perez-Cruz, F., & Shin, H. S. (2025). *Putting AI agents through their paces on general tasks* (BIS Working Papers No. 1245). Bank for International Settlements. https://www.bis.org/publ/work1245.htm
PwC Middle East. (2024). Agentic AI—the new frontier in GenAI: An executive playbook. https://www.pwc.com/m1/en/publications/agentic-ai-the-new-frontier-in-genai.html
Robertson, S., & Zaragoza, H. (2009). The Probabilistic Relevance Framework: BM25 and beyond. Foundations and Trends® in Information Retrieval, 3(4), 333–389. https://doi.org/10.1561/1500000019
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025). AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges. Information Fusion, 126, 103599. https://doi.org/10.1016/j.inffus.2025.103599
Syed, R., Suriadi, S., Adams, M., Bandara, W., Leemans, S. J., Ouyang, C., Ter Hofstede, A. H., Van De Weerd, I., Wynn, M. T., & Reijers, H. A. (2019). Robotic Process Automation: Contemporary themes and challenges. Computers in Industry, 115, 103162. https://doi.org/10.1016/j.compind.2019.103162
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., & Wen, J. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6). https://doi.org/10.1007/s11704-024-40231-1
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., V., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35, 24824-24837.
Wiesinger, J., Marlow, P., & Vuskovic, V. (2024). Agents [White paper]. Google. Retrieved December 14, 2024, from https://www.kaggle.com/whitepaper-agents
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., Zheng, R., Fan, X., Wang, X., Xiong, L., Zhou, Y., Wang, W., Jiang, C., Zou, Y., Liu, X., . . . Gui, T. (2025). The rise and potential of large language model based agents: a survey. Science China Information Sciences, 68(2). https://doi.org/10.1007/s11432-024-4222-0