自主智能系统的增量一致性执行
Incremental Consistency Execution for Autonomous Intelligent Systems
- KunlunMeta（昆仑万维）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对长时程自主智能系统状态变化导致的重执行冗余问题，提出基于任务事实契约、字段级依赖掩码和不变域的增量一致性执行方法，仅重算受影响字段，显著降低开销并保持高一致性。
AI中文摘要：
长时程自主智能系统依赖异构组件，如大型语言模型、数据库、外部API和规则引擎，而其外部状态在执行过程中持续变化。每次变化后重新执行整个工作流会引入大量冗余计算。本文提出了一种基于任务事实契约、字段级依赖掩码和状态扰动结果不变域的增量一致性执行方法。在初始验证执行后，系统为关键输入构建保守的不变域，并利用这些不变域判断下游结果是否可以在不重新调用昂贵组件的情况下安全更新。当需要重新执行时，仅重新计算受影响的最小输出字段，且等价性屏障可防止不必要的下游传播。提交时的版本一致性门进一步确保了具有副作用操作的安全性。在工业故障诊断、企业分析和基于LLM的多工具助手上的实验表明，所提方法显著减少了昂贵组件的调用和端到端延迟，同时保持了高一致性和低错误复用率。
英文摘要：
Long-horizon autonomous intelligent systems rely on heterogeneous components such as large language models, databases, external APIs, and rule engines, while their external states continuously change during execution. Re-executing the entire workflow after every change introduces substantial redundant computation. This paper proposes an incremental consistency execution method based on task fact contracts, field-level dependency masks, and state perturbation result invariant domains. After an initial verified execution, the system constructs conservative invariant domains for critical inputs and uses them to determine whether downstream results can be safely renewed without re-invoking expensive components. When re-execution is required, only the smallest affected output fields are recomputed, and an equivalence barrier prevents unnecessary downstream propagation. A submission-time version consistency gate further ensures the safety of side-effecting actions. Experiments on industrial fault diagnosis, enterprise analytics, and LLM-based multi-tool assistants show that the proposed method significantly reduces expensive component calls and end-to-end latency while maintaining high consistency and low incorrect-reuse rates.
