AI 中文总结
针对企业智能体基于过期快照计算可能产生未经授权效应的问题，提出提交时拒绝-重跑语义，将权威服务作为唯一效应权威，结合乐观并发控制与事务性发件箱，实验验证了其有效性与回退机制。
AI 中文摘要
企业智能体可以从策略、事实、任务状态、模型、工具和验证器的快照中计算数秒或数小时，而这些快照可能在其工作到达外部世界之前就已发生变化。因此，仅凭完成并不能赋予机构权威。我们将智能体视为提案生产者，并将一个逻辑上权威的服务作为受治理效应的唯一权威。在受理时，该服务将提案声明的依赖关系和组件清单与当前状态进行比较，应用当前的验证器，并要么为发件箱调度保留一个幂等效应，要么拒绝受影响的过期工作以进行重新同步和重跑。未受影响的工作可以继续；丢失的响应通过规范裁决和回执来解决。该协议组合了乐观并发控制、语义验证和事务性发件箱调度。其独特的读取集包括规范权威以及生成提案的模型组件。我们通过一个已实现的受治理工作生命周期、一个本地权威、发件箱和协调组合，以及一个在无法完全调解时委托效应权威的多进程回退来评估该设计。本地组合保留了选择性回退、未受影响的工作、重试和重启恢复以及包重建。完全调解产生了18条权威命令和18个外部效应。直接凭据分支产生了八个额外效应，全部通过独立的日志协调检测到，且在调解控制中无一被误检。结果支持提交时的拒绝-重跑语义，并揭示了委托受理所带来的时钟、租约、排序和法定人数义务。这些结果并未确立对绕过效应的预防或逆转、外部日志完整性、生产吞吐量、广域可用性、语义完整性或验证器正确性。
英文摘要
Enterprise agents can compute for seconds or hours from a snapshot of policy, facts, task state, models, tools, and verifiers that may change before their work reaches the world. Completion alone therefore cannot confer institutional authority. We treat agents as proposal producers and a logically authoritative service as the sole authority for governed effects. At admission, the service compares a proposal's declared dependencies and component manifest with current state, applies the current verifier, and either reserves an idempotent effect for outbox dispatch or rejects affected stale work for resynchronization and rerun. Unaffected work may continue; lost responses resolve through canonical verdicts and receipts. The protocol composes optimistic concurrency control, semantic verification, and transactional outbox dispatch. Its distinctive read set includes normative authority and the model components that produced the proposal. We evaluate the design through an implemented governed-work lifecycle, a local authority, outbox, and reconciliation composition, and a multi-process fallback that delegates effect authority when complete mediation is unavailable. The local composition preserved selective fallback, unaffected work, retry and restart recovery, and package reconstruction. Complete mediation produced 18 authority commands and 18 external effects. Direct-credential arms produced eight additional effects, all detected with independent journal reconciliation and none falsely detected in the mediated control. The results support commit-time reject-and-rerun semantics and expose the clock, lease, ordering, and quorum obligations introduced by delegated admission. They do not establish prevention or reversal of bypass effects, external-journal completeness, production throughput, wide-area availability, semantic completeness, or verifier correctness.
Comments15 pages, 6 tables. Design and controlled systems evidence for commit-time authority, reject-and-rerun, outbox dispatch, reconciliation, and delegated fallback
