DNative-Twin：用于可重构智能体决策的决策图与数字孪生

中文摘要 AI 辅助

AI智能体越来越多地收集证据、调用工具、应用约束并生成决策，而这些决策可能会被人或软件付诸行动。仅最终输出无法显示是哪项证据、工具状态、规则、授权或行动路径产生了该输出。我们提出DNative-Twin，一种图原生数字孪生，它将已确定的智能体决策记录为类型化轨迹，并在声明的条件下重新执行其决策机制。该图链接了智能体观察到的状态、它遵循的路径以及最终行动背后的授权。该孪生体同步这些信息、隔离地重放该机制，并在受控变化下对其进行比较。我们使用三个公开流程日志和受控重放套件，在企业决策流程中实例化该框架。实验确定了一个特定故障：图结构可定位所表示的变化，但无法确定未观察到的工具状态的后果。在包含300个注入实例的三条件受控实验中，当添加重放契约状态时，未解决分歧召回率从0提高到0.667，当同时提供验证结果时，该值提高到1.0；保留集不包含关键类实例。在500至5000个BPI 2020案例中，在报告的平台上，中位数端到端时间从0.794秒增加到8.889秒。这些结果明确了图结构、重放上下文和验证证据在审查决策机制中的不同作用。

英文摘要

AI agents increasingly gather evidence, invoke tools, apply constraints, and produce decisions that people or software may commit to action. A final output alone cannot show which evidence, tool state, rule, authorization, or action path produced it. We present DNative-Twin, a graph-native digital twin that records a committed agentic decision as a typed trajectory and re-executes its decision mechanism under declared conditions. The graph links the state observed by the agent, the path it followed, and the authority behind the resulting action. The twin synchronizes this information, replays the mechanism in isolation, and compares it under controlled changes. We instantiate the framework in enterprise decision processes using three public process logs and controlled replay suites. The experiments identify a specific failure: graph structure localizes represented changes but cannot determine the consequence of an unobserved tool state. In a three-condition controlled experiment with 300 injected instances, unresolved-divergence recall increased from 0 to 0.667 when replay-contract state was added and to 1.0 when verification results were also available; the held-out set contained no critical-class instance. Across 500--5,000 BPI 2020 cases, median end-to-end time increased from 0.794 to 8.889 seconds on the reported platform. These results separate the roles of graph structure, replay context, and verification evidence in reviewing a decision mechanism.

发表机构

• Qingdao University（青岛大学）
• Shandong University（山东大学）
• Hangzhou Shujiao Technology Partnership (Limited Partnership)（杭州数教科技合伙企业（有限合伙））
• Changchun University of Technology（长春工业大学）

机构由 AI 辅助整理，请以论文原文为准。