Autonomous Agents in International Payment Flows
Keywords:
Cross-Border Payments, Autonomous Financial Agents, Agent-Based Orchestration, Digital Identifiers, Tokenized Services, Transaction Negotiation Protocols, Latency Optimization, Regulatory Compliance Verification, Service-Level Agreement Enforcement, Multi-Institution Payment Networks, Transaction Lifecycle Management, Agent-Mediated Settlement, Dynamic Service Discovery, Interoperable Financial Silos, Payment Message Modernization, Compliance-Aware Orchestration, Decentralized Payment Coordination, Risk Of Agent Abuse, Real-Time Transaction Monitoring, Next-Generation Payment Architectures.Abstract
Cross-border payments are a core component of the global economy, relying on a complex network of banks and financial institutions to process transactions that range from a few seconds to several days via static APIs. Calls to modernize this system are widespread, yet current approaches offer only marginal improvement. Proposals built around digital identifiers and tokenization typically focus on changes to payment messaging formats or settlement mechanisms. Autonomous financial agents offer a different perspective on the problem, operating across institutional silos and handling transactions individually rather than in batches. In agent-based cross-border payment orchestration, individual agents act as digital representatives of the services they offer: service availability, terms, and costs are negotiated dynamically, and each transaction is managed end-to-end, from initiation through settlement. While this orchestration model offers meaningful advantages, fully realizing it raises concerns that merit closer examination.
Balancing the trade-off between minimizing overall latency and ensuring straightforward verification of compliance with regulations and service-level agreements requires a well-designed initiation-and-negotiation protocol. Because agents function as service gateways across the transaction lifecycle — from initiation to final settlement — certain steps normally handled through explicit exchange must instead be inferred by interacting agents. Future research should address the development of transaction-mechanism capacity suited to agent-based systems, ongoing measurement of latency and transaction volume within current architectures, and the real or perceived risks of misuse in agent-based orchestration. Resolving these issues would support broader adoption of autonomous agents in financial services and lay the groundwork for their eventual use in cross-border payments.
References
1. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations.
2. Schick, T., Dwivedi-Yu, J., Dessi, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36.
3. Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., Zhang, S., Deng, X., Zeng, A., Du, Z., Zhang, C., Shen, S., Zhang, T., Su, Y., Sun, H., Huang, M., Dong, Y., & Tang, J. (2024). AgentBench: Evaluating LLMs as agents. International Conference on Learning Representations.
4. MANGALAMPALLI, B. M., KOLLA, S. H., APPA RAO NAGUBANDI, D. R., & 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, 32(S9 (2025): Posted 15 December), 3070-3086.
5. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., Awadallah, A. H., White, R. W., Burger, D., & Wang, C. (2024). AutoGen: Enabling next-gen LLM applications via multi-agent conversation. Proceedings of the 2024 International Conference on Learning Representations Workshop on Large Language Model Agents.
6. Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S. K. S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., & Schmidhuber, J. (2024). MetaGPT: Meta programming for a multi-agent collaborative framework. International Conference on Learning Representations.
7. Wang, S., Ding, H., & Chen, H. (2023). Large language models in finance: A survey. Proceedings of the Fourth ACM International Conference on AI in Finance, 374–382.
8. Wu, S., Irsoy, O., Lu, S., Dabravolski, V., Dredze, M., Gehrmann, S., Kambadur, P., Rosenberg, D., & Mann, G. (2023). BloombergGPT: A large language model for finance. arXiv preprint arXiv:2303.17564.
9. 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.
10. Dong, Y., Wu, F., Zhang, K., Dai, Y., Zhang, S., Ye, W., Chen, S., & Cheng, Z.-Q. (2025). Large language model agents in finance: A survey bridging research, practice, and real-world deployment. Findings of the Association for Computational Linguistics: EMNLP 2025, 17889–17907.
11. Aldasoro, I., & Desai, A. (2025). AI agents for cash management in payment systems. Bank for International Settlements Working Paper No. 1310.
12. Davidovic, S., & Tourpe, H. (2025). How agentic AI will reshape payments. IMF Notes, 2025(001).
13. Adrian, T., Garratt, R., He, D., & Mancini-Griffoli, T. (2023). Trust bridges and money flows. Bank for International Settlements Working Paper No. 1112.
14. Arner, D. W., Buckley, R. P., Lammer, T., & Zetzsche, D. A. (2022). Building regional payment areas: The single rule book approach. Bank for International Settlements Working Paper No. 1016.
15. Anker-Sørensen, L., Passador, M. L., Wehrli, A., & Zetzsche, D. A. (2022). DLT-based enhancement of cross-border payment efficiency: A legal and regulatory perspective. Bank for International Settlements Working Paper No. 1015.
16. Auer, R., Haene, P., & Holden, H. (2021). Multi-CBDC arrangements and the future of cross-border payments. Bank for International Settlements Papers No. 115.
17. Mangalampalli, B. M., Kolla, S. K., Bandi, V. D. V. K., Yandamuri, U. S., & Rani, P. S. (2025). Designing Intelligent Healthcare Ecosystems through Adaptive Data Integration and Autonomous Learning Systems. Vascular and Endovascular Review, 8(20s), 330-347.
18. Bech, M. L., Faruqui, U., & Shirakami, T. (2020). Payments without borders. Bank for International Settlements.
19. Lammer, T., Rees, D., Rice, T., & Shirakami, T. (2025). Enhancing cross-border payments: State of play and way forward. Bank for International Settlements Bulletin No. 119.
20. Garratt, R., Koo Wilkens, P., & Shin, H. S. (2024). Next generation correspondent banking. Bank for International Settlements Bulletin No. 87.
21. Van Hee, K., Kosse, A., Wierts, P., & Wijngaard, J. (2025). Let's speak the same language: A formally defined model to describe and compare payment system architectures. Bank for International Settlements Working Paper No. 1259.
22. Kabadjova, B. A., Badev, A., Bastos, S. B., Benos, E., Cepeda-López, F., Chapman, J. T. E., Diehl, M., Duca-Radu, I., Garratt, R., Heijmans, R., Kosse, A., Martin, A., Nellen, T., Nilsson, T., Paulick, J., Pustelnikov, A., Rubem do Coutto Bastos, M., & Testi, S. (2023). Intraday liquidity around the world. Bank for International Settlements Working Paper No. 1089.
23. Di Iorio, A., Fitzgerald, E., Lammer, T., & Rice, T. (2024). Regional payment infrastructure integration: Insights for interlinking fast payment systems. Bank for International Settlements.
24. Fitzgerald, E., Illes, A., & Lammer, T. (2024). Steady as we go: Results of the 2023 CPMI cross-border payments monitoring survey. Bank for International Settlements.
25. Kim, S. S., & Yang, S. (2024). Accuracy improvement in financial sanction screening: Is natural language processing the solution? Frontiers in Artificial Intelligence, 7, 1374323.
26. Motie, S., & Raahemi, B. (2024). Financial fraud detection using graph neural networks: A systematic review. Expert Systems with Applications, 240, 122156.
27. 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.
28. Shih, Y.-C., Dai, T.-S., Chen, Y.-P., Ti, Y.-W., Wang, W.-H., & Kuo, Y. (2025). Fund transfer fraud detection: Analyzing irregular transactions and customer relationships with self-attention and graph neural networks. Expert Systems with Applications, 259, 125211.
29. Bin Sulaiman, R., Schetinin, V., & Sant, P. (2022). Review of machine learning approach on credit card fraud detection. Human-Centric Intelligent Systems, 2, 55–68.
30. Ileberi, E., Sun, Y., & Wang, Z. (2022). A machine learning based credit card fraud detection using the GA algorithm for feature selection. Journal of Big Data, 9, Article 24.
31. Benchaji, I., Douzi, S., El Ouahidi, B., & Jaafari, J. (2021). Enhanced credit card fraud detection based on attention mechanism and LSTM deep model. Journal of Big Data, 8, Article 151.
32. Dang, T. K., & Tran, T. C. (2021). Machine learning based on resampling approaches and deep reinforcement learning for credit card fraud detection systems. Applied Sciences, 11(21), 10004.
33. Khelifa, M., & Gharbi, A. (2021). Identification of non-typical international transactions on bank cards of individuals using machine learning methods. Procedia Computer Science, 190, 178–183.
34. Lokanan, M. E. (2023). Predicting mobile money transaction fraud using machine learning algorithms. Applied AI Letters, 4(1), e85.
