arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.24068cs.MAcs.CL
收藏

一种基于LLMs的新型分层多智能体系统用于支付

A Novel Hierarchical Multi-Agent System for Payments Using LLMs

School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算机与信息学院);Research and Development, Mastercard(万事达卡研发部)

Joon Kiat Chua, Donghao Huang, Zhaoxia Wang

AI总结:

本文提出HMASP系统,通过分层多智能体架构实现端到端支付流程自动化,采用模块化设计和协调协议,首次实现基于LLM的支付智能体全流程。

摘要:

大型语言模型(LLM)智能体,如OpenAI的Operator和Claude的Computer Use,能够自动化工作流但无法处理支付任务。现有智能体解决方案已引起广泛关注;然而,即使最新方法在实现端到端智能体支付工作流方面仍面临挑战。为此,本研究提出分层多智能体支付系统(HMASP),提供端到端智能体方法完成支付工作流。所提出的HMASP利用开放式或专有LLM,并采用由对话支付智能体(CPA - 第一智能体层级)、监督智能体(第二智能体层级)、路由智能体(第三智能体层级)和流程摘要智能体(第四智能体层级)组成的模块化架构。CPA作为中央入口点,处理所有外部请求并协调后续任务跨层级执行。HMASP集成了使智能体和层级间任务执行模块化的架构模式,包括共享状态变量、解耦消息状态和结构化交接协议,以促进智能体和工作流间的协调。实验结果证明了所提HMASP的可行性。据我们所知,HMASP是首个基于LLM的多智能体系统实现端到端智能体支付工作流。本工作为将智能体能力扩展到支付领域奠定了基础。

英文摘要:

Large language model (LLM) agents, such as OpenAI's Operator and Claude's Computer Use, can automate workflows but unable to handle payment tasks. Existing agentic solutions have gained significant attention; however, even the latest approaches face challenges in implementing end-to-end agentic payment workflows. To address this gap, this research proposes the Hierarchical Multi-Agent System for Payments (HMASP), which provides an end-to-end agentic method for completing payment workflows. The proposed HMASP leverages either open-weight or proprietary LLMs and employs a modular architecture consisting of the Conversational Payment Agent (CPA - first agent level), Supervisor agents (second agent level), Routing agents (third agent level), and the Process summary agent (fourth agent level). The CPA serves as the central entry point, handling all external requests and coordinating subsequent tasks across hierarchical levels. HMASP incorporates architectural patterns that enable modular task execution across agents and levels for payment operations, including shared state variables, decoupled message states, and structured handoff protocols that facilitate coordination across agents and workflows. Experimental results demonstrate the feasibility of the proposed HMASP. To our knowledge, HMASP is the first LLM-based multi-agent system to implement end-to-end agentic payment workflows. This work lays a foundation for extending agentic capabilities into the payment domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑