SABRE：预算约束下选择分布外检测器的多智能体方法
SABRE: A Multi-Agent Approach for Selecting Out-of-Distribution Detectors Under a Budget
AI总结：
SABRE是一种多智能体方法，可在预算约束下针对视觉-语言模型的分布外检测，自动选择各领域最优检测器，解决固定检测器跨领域失效的问题，实现可靠检测。
AI中文摘要：
针对视觉-语言模型的事后分布外（OOD）检测假设，在基准测试中选择的检测器部署后仍能保持可靠性。我们证明这一假设在不同领域均不成立：在单个冻结编码器上，某一领域表现最优的检测器在另一领域可能失效，将分布内输入判定为比真实异常值更异常，且最优检测器会随领域变化，因此固定选择无法在所有领域保持可靠。我们提出SABRE（Selective Agentic Budgeted Reliability Ensemble，选择性智能体预算约束可靠性集成），该方法在推理时用针对不同场景的选择替代固定选择。三个语言模型智能体在有限查询预算下对事后检测器库进行推理：选择器决定接下来咨询哪个检测器，报告器整合每个输入的证据，分析器在部署领域留出的小标记样本（与测试数据不重叠）上校准检测器可靠性，在不观察已评分输入标签的情况下对选择和聚合进行加权。该库包含我们提出的四个多模态密度检测器。通过从数据中推断操作场景，SABRE无需先验知识即可跟踪每个领域的最优检测器，在传统检测器失效的场景中恢复可靠检测，在传统检测器有效的场景中收敛至该检测器。组件分析显示智能体具有互补性：报告器的反馈带来持续增益，分析器的校准对防止失效起决定性作用，可排除不可靠检测器，使聚合不再抵消可靠检测器的效果。由于固定规则无法跨领域信任，可靠性必须在部署时建立而非从基准测试中假设，SABRE证明这一过程可自动实现。
英文摘要：
Post-hoc out-of-distribution (OOD) detection for vision-language models assumes that a detector chosen on a benchmark stays reliable once deployed. We show this fails across domains: on a single frozen encoder, a detector that leads in one domain can invert in another, scoring in-distribution inputs as more anomalous than genuine outliers, and the best detector changes from domain to domain, so no fixed choice is reliable throughout. We introduce SABRE (Selective Agentic Budgeted Reliability Ensemble,) which replaces this fixed choice with per-regime selection at inference. Three language-model agents reason over a library of post-hoc detectors under a bounded query budget: a Selector chooses which detector to consult next, a Reporter consolidates the evidence for each input, and an Analyst calibrates detector reliability on a small labeled sample held out from the deployment domain and disjoint from the test data, weighting selection and aggregation without ever observing a scored input's label. The library includes four multimodal density detectors we propose. Inferring the operating regime from data, SABRE tracks the strongest detector in each domain without prior knowledge of it, recovering reliable detection where a conventional detector inverts and converging to that detector where it is sound. A component analysis shows the agents are complementary: the Reporter's feedback yields consistent gains, and the Analyst's calibration is decisive against inversion, ruling out unreliable detectors so that aggregation no longer cancels the sound ones. Since no fixed rule can be trusted across domains, reliability must be established at deployment rather than assumed from a benchmark, and SABRE shows this can be done automatically.
