为智能业务流程代理构建可共享的组织记忆系统
Organizational Memory for Agentic Business Process Execution
- 设计共享知识层，让代理统一访问企业专属流程知识
- 在采购场景验证，显著减少规则重复与更新延迟
- 适合需要跨系统协同的大型企业流程自动化
基于大模型的智能代理为突破传统规则系统的局限提供了新可能。然而，通用大模型缺乏企业特有的执行知识，这些知识通常分散在政策文档、流程图和标准操作手册等人为资料中。若将知识硬编码进单个提示或代理检索配置，会导致知识孤岛和规则重复，难以实现跨代理的一致更新与学习。为此，我们提出构建面向智能业务流程执行的组织记忆：一个共享、受控、可被代理消费的动态组织知识参考层。论文定义了该记忆系统的必要需求，提出了其构建与使用架构，并在采购场景的原型验证中展示了有效性。
原文摘要 · Abstract (English)
LLM-based agents offer new opportunities for automating business process execution beyond the limits of rule-based systems. However, general-purpose LLMs lack the organization-specific knowledge required for reliable execution, which is typically fragmented across human-oriented artifacts such as policies, process models, and standard operating procedures. While such knowledge can technically be encoded in individual prompts or agent-specific retrieval setups, this approach does not scale in enterprises, as it gives rise to knowledge silos and rule duplicates, and makes consistent updates and learning across agents difficult. We argue that this calls for an organizational memory for agentic business process execution: a shared, governed, and agent-consumable reference layer of evolving organization-specific procedural knowledge about how work should be executed. We derive requirements for such a memory, propose an architecture for its curation and consumption, and demonstrate its effectiveness in a proof-of-concept based on a procurement scenario.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。