Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large language or multimodal models to finding abnormal patterns in sequential data. Public anomaly detection benchmarks typically provide interval annotations but not natural-language rationales, making it difficult to fine-tune VLMs to produce grounded, interpretable decisions. To address this gap, we construct VisAnomBench, a curated benchmark built from public time-series datasets and augmented with high-quality anomaly explanations selected from multiple large VLMs using fine-grained, task-specific rewards. Through fine-tuning on this benchmark, we develop VisAnomReasoner, a parameter-efficient VLM for time-series anomaly detection. Experimental results on VisAnomBench show that VisAnomReasoner achieves more accurate anomaly localization and consistently outperforms all baselines, with improvements of at least 21.23 and 23.87 percentage points in precision and F1, respectively. Additional experiments on the TSB-AD-U benchmark demonstrate strong cross-benchmark generalization, with VisAnomReasoner improving precision and F1 by 9.57 and 13.39 percentage points, respectively.

翻译：近期视觉-语言模型（VLM）在众多任务中取得了显著进展，然而先前研究表明，将大型语言或多模态模型应用于序列数据异常模式检测时，其性能表现并不理想。公开的异常检测基准数据集通常仅提供区间标注而非自然语言解释，这使得难以对VLM进行微调以获得具有可解释性的可靠决策。为填补这一空白，我们构建了VisAnomBench——一个基于公开时间序列数据集构建的精选基准，并利用基于细粒度任务特定奖励从多个大型VLM中筛选的高质量异常解释进行增强。通过在该基准上进行微调，我们开发了VisAnomReasoner——一种面向时间序列异常检测的参数高效VLM。在VisAnomBench上的实验结果表明，VisAnomReasoner实现了更精确的异常定位，并在所有基线方法中持续保持最优性能，精确率和F1值分别至少提升21.23和23.87个百分点。在TSB-AD-U基准上的额外实验验证了其跨基准的强泛化能力，VisAnomReasoner将精确率和F1值分别提升了9.57和13.39个百分点。