用可验证的流程图提升智能自动化可靠性，防止错误累积。
GraphFlow: An Architecture for Formally Verifiable Visual Workflows Enabling Reliable Agentic AI Automation
- 将流程图作为可执行规范，编译时检查契约，确保逻辑正确。
- 三年临床试点完成8728次流程，成功率97.08%，失败多由外部系统引发。
- 支持回放、重试和审计，适合医疗等高可靠场景使用。
GraphFlow 是一个视觉工作流系统，旨在提升多步骤、关键任务中智能代理自动化系统的可靠性。在理想独立步骤模型下，10步流程每步90%可靠性，成功仅35%。现有平台虽具备持久执行与可观测性，但缺乏语义正确性保障；而智能系统推理时规划，行为易受提示影响且难以审计。GraphFlow 将工作流图视为可执行规范，统一定义数据范围、执行语义与监控机制。编译时，限定类别的流程图生成可复用自动化，其契约（前提、后置条件及组合义务）可在准入前进行形式化验证。运行时，持久化引擎以追加只读日志记录结果，可在系统边界强制执行契约，支持回放、重试与审计。泳道显式划分信任边界，分离已验证逻辑与外部系统、人工判断及AI决策。在三个临床站点为期一年的试点中，早期原型完成8,728次队列工作流运行，成功率达97.08%，观测到的失败主要集中在外部集成环节。本文所述的形式语义与证明准入模型已明确描述，正积极开发中。已验证核心的评估将留待未来工作。
原文摘要 · Abstract (English)
GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps, a ten-step process with 90% per-step reliability completes successfully only 35% of the time. Existing workflow platforms provide durable execution and observability but offer few semantic correctness guarantees, while agentic systems plan at inference time, making behavior sensitive to prompt variation and difficult to audit. GraphFlow is designed to address this gap by treating workflow diagrams as the executable specification, a single artifact defining data scope, execution semantics, and monitoring. At compile time, a restricted class of diagrams is specified to produce reusable automations whose contracts (preconditions, postconditions, and composition obligations) are intended to be proof-checked before admission to a shared library. At runtime, a durable engine records outcomes in an append-only event log and can enforce contracts at system boundaries, supporting replay, retries, and audit. Swimlanes make trust boundaries explicit, separating verified logic from external systems, human judgment, and AI decisions. A year-long pilot across three clinical sites executed 8,728 cohort-enrolled workflow runs with a 97.08% completion rate under an early prototype without the verified-core subsystem; observed failures were localized primarily to external integrations. The formal semantics and proof-checked admission model described here are specified and under active development. Evaluation of the verified core is reserved for future work.
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。