跳到正文
arXiv cs.AI· Tord Johan Eide, Einar Holt·· 2 小时前AI 评分31

ARC-2:通过 Delta 管理实现自主系统的持续合规

ARC-2: Continuous Compliance Through Delta Management

AI 导读

这篇论文提出 Delta 管理,一个持续治理框架,通过测量系统当前运行状态与其认证基线(定义为区域而非固定点)的偏差,以持续监控取代静态认证。框架包含四项扩展:CRAB 评估纳入最坏已验证行为偏差并隔离异常值、分层触发分类、分级安全过渡协议(将撤回运行授权与物理关机分离),以及将环境漂移超出认证 ODD 作为触发再认证的条件。

正文 · 原文

View PDF

Abstract:ARC 1 introduced a three-layer governance architecture for autonomous systems comprising model safety validation, cognitive certification (CRAB), and operational authorization (LEA). However, it did not address how compliance should be maintained after deployment.
This paper introduces Delta Management, a continuous governance framework that measures deviations between a system's current operational state and its certified baseline, defined as a region rather than a fixed point. Compliance is assessed through continuous monitoring instead of static certification.
Four extensions are proposed. First, CRAB evaluation incorporates the worst verified behavioral deviations, with isolated outliers quarantined pending confirmation to prevent unjustified restrictions. Second, a layered trigger taxonomy distinguishes hard safety violations, critical single-dimension failures, correlated multi-system degradation, and risk-weighted composite indicators, each triggering proportionate responses. Third, a graduated safe transition protocol separates withdrawal of operational authorization from physical shutdown, consistent with established safety standards and EU AI Act requirements. Fourth, environmental delta is introduced as a distinct baseline validity condition: environmental drift beyond the certified Operational Design Domain (ODD) triggers recertification or ODD revision rather than automatic authority contraction.
Together, these extensions transform ARC from a deployment-time certification architecture into a continuous framework for monitoring, evaluating, and enforcing compliance throughout the operational lifecycle of autonomous systems. The framework addresses the continuous compliance obligations established by EU AI Act Article 72(2).
Comments: 22 pages. Conceptual framework for continuous compliance monitoring, behavioral drift detection, and operational authorization of autonomous robotic systems. Extends ARC-1 (arXiv:2609.12932)
Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
Cite as: arXiv:2611.21811 [cs.RO]
  (or arXiv:2611.21811v1 [cs.RO] for this version)
  https://doi.org/10.48550/arXiv.2611.21811

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tord Eide [view email]
[v1] Mon, 16 Nov 2026 19:25:00 UTC (233 KB)

来源:arXiv cs.AI · arxiv.org