ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response
Time series question-answering (TSQA), in which we ask natural language questions to infer and reason about properties of time series, is a promising yet underexplored capability of foundation models. In this work, we present ARFBench, a TSQA benchmark that evaluates the understanding of multimodal foundation models (FMs) on time series anomalies prevalent in software incident data. ARFBench consists of 750 questions across 142 time series and 5.38M data points from 63 production incidents sourced exclusively from internal telemetry at Datadog. We evaluate leading proprietary and open-source LLMs, VLMs, and time series FMs and observe that frontier VLMs perform markedly better than existi...
| Authors | Stephan Xie, Ben Cohen, Mononito Goswami et al. |
|---|---|
| Primary category | cs.LG |
| Published | 23 April 2026 |
| Last updated at source | 30 April 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- Datadog/ARFBenchDataset · cited by
Models and datasets referencing this paper
- Datadog/ARFBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.