独立仲裁团的幻象：智能体仲裁团中的认知故障域与关联认知失败
The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums
浏览论文内容
中文总结 AI 辅助
本文针对智能体仲裁团中存在的复制不代表认知冗余的问题，提出认知故障域与结构认知割概念，设计DAQC控制器，通过理论分析与仿真验证，提供120任务基准，为高风险授权场景的可靠性提供保障。
中文摘要 AI 辅助
多智能体仲裁团被广泛用于授权高风险基础设施和政策变更，但不同的评审员通常共享上游遥测数据、文档或工具后端。当上游输入发生故障时，多个投票会因单一损坏原因而崩溃：复制并不意味着认知冗余。我们引入认知故障域（Epistemic Fault Domains，EFD）和结构认知割κ_E，该参数量化了相对于显式认知故障基，覆盖授权联盟所需的建模根故障的最小数量。在封闭因果核算、保守暴露和授权对齐的条件下，κ_E为语义妥协所需的根数量（κ_S）提供下界。我们证明，任意大的仲裁团都可保持κ_E=1，识别共享血统永远不会增加可信弹性，且在兼容暴露扩展下，按固定阈值添加投票者无法增大该割。最后，我们设计依赖感知仲裁团控制器（Dependency-Aware Quorum Controller，DAQC）以在运行时准入阶段强制实施结构割，通过分析推导和仿真评估其机制，并提供包含120个任务的冻结外部基准套件。
英文摘要
Multi-agent quorums are widely used to authorize high-stakes infrastructure and policy mutations, yet distinct reviewers often share upstream telemetry, documents, or tool backends. When upstream inputs fail, multiple votes collapse onto a single corrupted cause: replication does not imply epistemic redundancy. We introduce Epistemic Fault Domains (EFDs) and the Structural Epistemic Cut κ_E, which quantifies the minimum number of modeled root faults whose exposure covers an authorizing coalition relative to an explicit Epistemic Fault Basis. Under closed causal accounting, conservative exposure, and authorization alignment, κ_E lower-bounds the number of roots required for semantic compromise (κ_S). We prove that arbitrarily large quorums can retain κ_E=1, that recognizing shared ancestry never increases credited resilience, and that adding voters at a fixed threshold cannot increase the cut under compatible exposure extensions. Finally, we design the Dependency-Aware Quorum Controller (DAQC) to enforce structural cuts at runtime admission, evaluate its mechanics via analytical derivations and simulations, and provide a frozen 120-task external benchmark suite.
