国际清算银行-支付系统中用于现金管理的AI代理（英）

BIS Working Papers No 1310 AI agents for cash management in payment systems by Iñaki Aldasoro and Ajit Desai Monetary and Economic Department November 2025 JEL classification: A12, C7, D83, E42, E58 Keywords: Generative AI, agentic AI, LLM, payments systems, liquidity management BIS Working Papers are written by members of the Monetary and Economic Department of the Bank for International Settlements, and from time to time by other economists, and are published by the Bank. The papers are on subjects of topical interest and are technical in character. The views expressed in this publication are those of the authors and do not necessarily reflect the views of the BIS or its member central banks. This publication is available on the BIS website (www.bis.org). © Bank for International Settlements 2025. All rights reserved. Brief excerpts may be reproduced or translated provided the source is stated. ISSN 1020-0959 (print) ISSN 1682-7678 (online) AI agents for cash management in payment systems*I˜naki Aldasoro1 and Ajit Desai1,2,⋆1Bank for International Settlements2Bank of CanadaNovember 10, 2025AbstractUsing prompt-based experiments with ChatGPT’s reasoning model, we evaluate whethera generative artificial intelligence (AI) agent can perform high-level intraday liquiditymanagement in a wholesale payment system.We simulate payment scenarios withliquidity shocks and competing priorities to test the agent’s ability to maintain pre-cautionary liquidity buffers, dynamically prioritize payments under tight constraints,and optimize the trade-off between settlement speed and liquidity usage.Our re-sults show that even without domain-specific training, the AI agent closely replicateskey prudential cash-management practices, issuing calibrated recommendations thatpreserve liquidity while minimizing delays. These findings suggest that routine cash-management tasks could be automated using general-purpose large language models,potentially reducing operational costs and improving intraday liquidity efficiency. Weconclude with a discussion of the regulatory and policy safeguards that central banksand supervisors may need to consider in an era of AI-driven payment operations.Keywords: Generative AI, agentic AI, LLM, payments systems, liquidity managementJEL Codes: A12, C7, D83, E42, E58*The views expressed in this paper are solely those of the authors and do not necessarily reflect those of the Bankfor International Settlements (BIS) or the Bank of Canada (BoC). We thank Narayan Bulusu, Jon Frost, Janet Jiang,Anneke Kosse, Christoph Meyer, Fernando Perez-Cruz, Jordan Press and Francisco Rivadeneyra for helpful commentsand suggestions. In addition, we thank participants of the following conferences and seminars for their comments andsuggestions: BoC Annual Economic Conference 2025, the 4th IFC Workshop on Data Science in Central Banking,BoC ECONDAT Fall 2025 Meeting - 7th Conference on Nontraditional Data, Machine Learni