用只读验证器控制多智能体系统完成状态，确保决策可审计且失败时闭合。
Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study
- 引入只读验证器作为准入控制，决定智能体提出的完成请求是否通过。
- 99.5%的验证事件成功通过，且失败时默认拒绝，保障安全。
- 适合关注系统可审计性与运行时控制的开发者或安全研究人员。
随着多智能体系统从短暂交互转向使用工具、具有专门角色和持久状态的工作流，完成状态成为运行时控制问题，而不仅是生成问题。本文研究了验证门控完成作为受控多智能体运行时的准入控制模式：智能体可提议完成，但由只读验证器决定是否接受。模糊或证据不足的情况默认拒绝，分包的状态与事件记录保留审计路径。我们分析了一个有限参考实现，探讨已释放证据对可审计、验证门控完成的支持程度。在已发布的验证完成片段中，已触发事件的验证成功率高达1,791/1,800 = 99.5%，此为针对触发验证事件的会计度量，非任务完成率或生产可靠性。任务级验证覆盖率无法计算；其中1,762/1,801条记录来自单一高负载报告集群；仅17个事件被标记为生产级。影子策略/治理验证器评估显示规则一致率为1,526/1,548 = 98.58%，安全继续预测中无误报（0/1,526），阻断精确率为2/518 = 0.39%，因此仍为建议性质。证据支持的结论仅限：在观察条件下，只读验证门与分包准入记录使完成决策可检查且失败闭合。关于部署运行、安全保证、结果收益、任务级覆盖、恢复效果或外部有效性的主张均不在研究范围。
原文摘要 · Abstract (English)
As multi-agent systems move from short interactions to tool-using workflows with specialized roles and persistent state, completion becomes a runtime-control problem rather than a purely generative one. This preprint studies verify-gated completion as an admission-control pattern for governed multi-agent runtimes: agents may propose completion, but a read-only verifier decides whether the claim is admitted. Ambiguous or weakly evidenced cases resolve fail-closed, while packetized state and event traces preserve an audit path. We examine one bounded reference implementation and ask what the released evidence can support about auditable, verify-gated completion. In the released verify-completed slice, the known-outcome invoked-event verify success share was 1,791/1,800 = 99.5%. This is an accounting measure over invoked verification events, not a task-completion, production-reliability, or benchmark-success rate. Task-level verify coverage is not computable; 1,762/1,801 rows came from one high-volume reporting cluster; and only 17 events were production-classified. A shadow Policy/Governance Verifier evaluation showed 1,526/1,548 = 98.58% rule agreement, 0/1,526 false-success among safe-to-proceed predictions, and blocked precision of 2/518 = 0.39%, so it remains advisory. The evidence supports a narrow conclusion: under observed conditions, a read-only verify gate plus packetized admission records made completion decisions inspectable and fail-closed. Claims about deployed operation, safety guarantees, outcome gains, task-level coverage, recovery effectiveness, or external validity remain outside scope.
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。