提出运行时数据质量门控机制，解决智能体因过时证据导致错误动作的问题。
SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediation
- 在行动前加入元数据感知的检查门，仅依赖下游结果修复缺陷
- 60%情况下，过时数据导致昂贵错误，且模型能力越高越无法察觉
- 适用于对数据可信度要求高的企业级智能体系统，如金融、供应链
智能体系统在执行任务时，若检索到有缺陷的证据，将引发代价高昂的错误行为。最危险的缺陷是元数据相关的：如过时价格或已被取代的记录，其内容格式正确，仅在新鲜度、来源或出处上出错。这类缺陷不会进入智能体上下文，且智能体无法质疑未看到的数据。在定价补货基准测试中，一个能力强的智能体在注入元数据缺陷后，约60%的时间会无声地将其转化为错误操作，且无任何数据质量警告或行为怀疑信号（AUC ≤ 0.50）。在四个推理成本相差约15倍的模型层级中，该错误率保持不变，表明能力提升并不带来更强的质疑能力。一种基于元数据的前置检查门可完全恢复其所覆盖信号的损失，但对其未覆盖信号无效。从任务决策几何推导出的模型无关预言机，能以0.015的平均绝对误差和0.876的皮尔逊相关系数准确预测错误率，覆盖15/16个测试单元。证据完整性是独立于模型能力的系统维度；缓解策略取决于执行位置与判断条件的覆盖范围。代码、冻结结果与确定性分析流水线已公开：https://github.com/besanson/dqSarc
原文摘要 · Abstract (English)
Agentic systems act, so a defect in the evidence they retrieve becomes a wrong action with a currency cost. The most dangerous enterprise defects are metadata-borne: a stale price or a superseded record, perfectly well-formed in the payload and betrayed only by freshness, lineage, or provenance. Such a defect never enters the agent's context, and an agent cannot doubt data it cannot see. On a priced replenishment benchmark, a competent agent silently converts an injected metadata-borne defect into a costly action about 60% of the time, with zero data-quality flags and behavioral doubt markers at chance (AUC <= 0.50). Across four model tiers spanning roughly 15x in inference price, the rate stays flat: capability does not buy skepticism. A metadata-aware pre-action gate with downstream-only remediation recovers the loss fully on the signals its predicates cover and not at all on those they miss. A model-free oracle derived from the task's decision geometry tracks the measured rates with MAE 0.015 (Pearson r = 0.876, interval coverage 15/16 cells), giving the flat ladder an analytical form. Evidence integrity is a systems axis distinct from model capability; mitigation depends on enforcement placement and predicate coverage. Code, frozen results, and a deterministic analysis pipeline: https://github.com/besanson/dqSarc
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。