提出设计阶段验证智能体工作流的方法，确保模块组合无逻辑错误。
Composing Verifiable Conceptual Models via Building Blocks: Towards Design-Time Verification of Agentic AI Workflows
- 将智能体工作流拆解为可复用模块，通过12条结构规则检查兼容性。
- 在48个含缺陷的工作流上检测出所有错误，即使任务被拆分也有效。
- 适合构建安全智能体系统的研究者与开发者使用。
智能体AI系统通过工作流架构协调多个基于大模型的智能体进行决策、工具调用和外部操作。尽管现有平台侧重运行时防护，但缺乏对设计阶段工作流的验证支持。从建模与仿真视角看，这相当于在未验证模块间是否协同的情况下拼装概念模型。本文提出一种设计时验证方法，将智能体工作流视为可复用构建块的组合，并通过12条结构规则检查其兼容性。我们实现了一个软件原型，在两个公开数据集上评估：48个已知存在设计缺陷的工作流，以及168个保持逻辑不变但改变图结构的变体。结果表明，该验证器能可靠检测违规行为，即使错误设计通过任务拆分等结构变换被隐藏。未来工作可将本验证机制与社区构建块库结合，实现更安全的智能体工作流组合。
原文摘要 · Abstract (English)
Agentic AI systems orchestrate multiple LLM-based agents through workflow architectures that coordinate decisions, tools, and external actions. While current platforms emphasize runtime safeguards, little support exists for verifying workflows during system design. From a Modeling \& Simulation perspective, this gap is analogous to composing conceptual models without verifying whether their building blocks interact coherently. We propose a design-time verification approach that models agentic workflows as compositions of reusable building blocks and checks their compatibility through twelve structural rules. We implemented these rules in a software prototype and evaluated them using two openly released datasets: 48 workflows with known design flaws and 168 variants that preserve workflow logic but alter graph structure. Results show that our verifier reliably detects violations even when flawed designs are obscured through structural transformations such as splitting tasks between agents. Future works could combine our verification with community repositories of building blocks to compose safe agentic workflows.
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。