面向可扩展且可管理的智能体运行时的以契约为中心的架构
A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes
浏览论文内容
中文总结 AI 辅助
针对企业AI部署的协调问题，本文提出以契约为中心的智能体运行时架构，含Skill等四个责任对象及P1假设，还提出可证伪的测量协议，目前无已完成的实现、实验等结果。
中文摘要 AI 辅助
企业AI部署是业务部门、应用与AI团队、测试、平台工程、基础设施、安全、运营及数据治理之间的协调问题。用例基准仅能展示单个智能体是否完成单个任务，却无法说明能力、模型、运行时机制、容量及企业数据的变更应如何共同归属、变更、接纳或验证。我们提出四个责任对象作为共享组织契约：Skill（可复用、带版本的能力与工作流资产）、Harness（运行时编译器与管控器）、Scaffold（执行/控制边界及非功能性需求（NFR）所有者），以及一个处于CIO独立管控的语义与遥测体系下的栈外部数据子层。运行时核心为A = <S, H, X>，数据子层位于该栈之外。核心贡献为一个有界、可证伪的假设P1（感知成本的能力-容量可分离性）：在声明的操作区域内，变更激活的能力可在预注册的等价裕度内保持容量-响应交互，而变更兼容的Scaffold容量可在非劣效裕度内保持能力语义，且所需控制措施需处于声明的执行预算内。六个设计条件成为可测量的义务，其覆盖范围、违规情况、不确定性、成本及排除项决定P1是否可判定。我们提出一种集群-周期随机交叉实验（平衡顺序、重置/洗脱、重复种子与故障 regime、集群感知不确定性），其包含四种状态判定：支持、证伪、条件工程或不确定。本文贡献了契约有界的运行时架构、源保留的数据子层及可证伪的测量协议，报告无已完成的实现、实验、数据集或测量结果。
英文摘要
Enterprise agentic systems must coordinate changing capabilities, execution capacity, and independently governed data. We define Skill, Harness, Scaffold, and an external data substrate as responsibility contracts. The central hypothesis, cost-aware capability-capacity separability, asks whether compatible capacity changes preserve semantic outcomes while capability changes preserve the capacity-response relationship within declared margins and enforcement budgets. We operationalize the data boundary through a source-oriented Data Wiki, an output-oriented Theme Wiki, and a versioned Intermediate Relation. Executable 5W1H+Which predicates bind source identity, validity, authorization, semantics, operations, relations, and evidence requirements. Request-bound tickets add execution-time revalidation and typed rejection. A conditional soundness argument states the required trust and atomicity assumptions; dependency invalidation makes change propagation explicit. A single-process reference model agrees with a declared specification oracle on all 1,024 combinations in a finite synthetic fault domain and passes five lifecycle checks. These are conformance results, not measurements of retrieval quality, production safety, or scaling. We specify a held-out data study and a cluster-period crossover with distinct supported, falsified, conditional-engineering, and inconclusive verdicts. The core separability hypothesis remains empirically untested.
发表机构
- PwC China AI Center（普华永道中国AI中心）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
