AI 中文总结
本研究提出一种决策特定审计方法，通过映射观察通道与产品价值对比来识别智能体选择中的委托盲点，实验显示模型报告引入不必要不确定性，强调保留结构化输入并诊断未解决决策。
AI 中文摘要
成功的智能体执行并不需要识别用户会重视的哪个未来产品改进。我们提出了一种决策特定的审计方法，该方法将声明的观察通道和产品价值对比映射到兼容区间和见证群体。其基础是已确立的识别和决策理论；贡献在于一个可执行的测量工作流及其局限性的受控研究。一个冻结的实验对共享合成任务上的两个固定模型快照发出4,800次请求。尽管执行准确性不同，所有36个保守的主要区间仍然未解决。一项探索性的2,400次调用后续记录提供的偏好，并解决了每个模型的九个比较中的三个。一个确定性提取器在没有模型调用或校准观察的情况下解决了九个中的七个，暴露了模型生成报告引入的不必要不确定性。进一步的14,400次受控多项式模拟区分了结构模糊性与弱识别和有限校准精度。我们提出了一种源标记的决策收据，并提供了一个离线查看器用于检查审计。这些结果激励保留决策相关的结构化输入，并在收集更多遥测数据之前诊断决策为何未解决。该研究不包含人类参与者或真实客户结果。完整证明、原始模型来源、受控实验和可复现分析随报告附上。
英文摘要
Successful agent execution need not identify which future product improvement its user would value. We present a decision-specific audit that maps a declared observation channel and product-value contrast to compatible intervals and witness populations. Its foundations are established identification and decision theory; the contribution is an executable measurement workflow and a controlled study of its limits. A frozen experiment makes 4,800 requests to two pinned model snapshots on shared synthetic tasks. All 36 conservative primary intervals remain unresolved despite different execution accuracy. An exploratory 2,400-call follow-up records supplied preferences and resolves three of nine comparisons per model. A deterministic extractor resolves seven of nine without model calls or calibration observations, exposing unnecessary uncertainty introduced by model-generated reports. A further 14,400 controlled multinomial simulations distinguish structural ambiguity from weak identification and finite calibration precision. We propose a source-labeled decision receipt and provide an offline viewer for inspecting the audit. These results motivate preserving decision-relevant structured input and diagnosing why a decision is unresolved before collecting more telemetry. The study contains no human participants or real customer outcomes. Full proofs, raw model provenance, controlled experiments, and reproducible analyses accompany the report.
Comments15 pages, 5 figures. Computational technical report with proofs and synthetic-task experiments; no human participants. Code: https://github.com/shi1720/delegation-blind-spot
