ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response

• URL: http://arxiv.org/abs/2604.21199v1
• Date: Thu, 23 Apr 2026 01:45:10 GMT
• Title: ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response
• Abstract summary: Time series question-answering (TSQA) is a promising yet underexplored capability of foundation models.<n>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.<n>We develop a novel TSFM + VLM hybrid prototype which we post-train on a small set of synthetic and real data that yields comparable overall F1 and accuracy with frontier models.
• Score: 33.890280378630884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 existing baselines; the leading model (GPT-5) achieves a 62.7% accuracy and 51.9% F1. We next demonstrate the promise of specialized multimodal approaches. We develop a novel TSFM + VLM hybrid prototype which we post-train on a small set of synthetic and real data that yields comparable overall F1 and accuracy with frontier models. Lastly, we find models and human domain experts exhibit complementary strengths. We define a model-expert oracle, a best-of-2 oracle selector over model and expert answers, yielding 82.8% F1 and 87.2% accuracy and establishing a new superhuman frontier for future TSQA models. The benchmark is available at https://huggingface.co/datasets/Datadog/ARFBench.

Related papers

• When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters [0.0]
  Foundation models outperform classical methods at every evaluated training fraction on 15 of 30 datasets.<n>One robust deployment rule requires no model training: if n_train 700 and seasonality is non-negligible, use FM zero-shot and skip fine-tuning.
  arXiv  Detail & Related papers  (2026-07-06T10:48:11Z)
• TSAQA: Time Series Analysis Question And Answering Benchmark [85.35545785252309]
  Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science.<n>We introduce TSAQA, a novel unified benchmark designed to broaden task coverage and evaluate diverse temporal analysis capabilities.
  arXiv  Detail & Related papers  (2026-01-30T17:28:56Z)
• In-Context and Few-Shots Learning for Forecasting Time Series Data based on Large Language Models [0.0]
  This paper investigates the performance of using LLM models for time series data prediction.<n>We train LLMs through in-context, zero-shot and few-shot learning and forecasting time series data with OpenAI tt o4-mini and Gemini 2.5 Flash Lite.<n>The findings indicate that TimesFM has the best overall performance with the lowest RMSE value (0.3023) and the competitive inference time (266 seconds)
  arXiv  Detail & Related papers  (2025-12-08T16:52:46Z)
• MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models [11.374098795890738]
  MoFE-Time integrates time and frequency domain features within a Mixture of Experts (MoE) network.<n>MoFE-Time has achieved new state-of-the-art performance, reducing MSE and MAE by 6.95% and 6.02% compared to the representative methods Time-MoE.<n>Our method achieves outstanding results on this dataset, underscoring the effectiveness of the MoFE-Time model in practical commercial applications.
  arXiv  Detail & Related papers  (2025-07-09T03:00:56Z)
• Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model [55.25659103706409]
  This framework achieves state-of-the-art performance for our designed foundation model, YingLong.<n>YingLong is a non-causal, bidirectional attention encoder-only transformer trained through masked token recovery.<n>We release four foundation models ranging from 6M to 300M parameters, demonstrating superior results in zero-shot tasks.
  arXiv  Detail & Related papers  (2025-05-20T14:31:06Z)
• APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay [86.01901238059261]
  APIGen-MT is a framework that generates verifiable and diverse multi-turn agent data.<n>We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters.<n>Our models outperform frontier models such as GPT-4o and Claude 3.5 on $tau$-bench and BFCL benchmarks.
  arXiv  Detail & Related papers  (2025-04-04T17:13:57Z)
• TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting [35.505530132151]
  Time Series Forecasting (TSF) is key functionality in numerous fields, such as financial investment, weather services, and energy management.<n>Many TSF methods require domain-specific data collection and model training and do not generalize well when applied in other domains.<n>Time Series Foundation Models (TSFMs) that are pre-trained on massive heterogeneous time series data aim to overcome these limitations.
  arXiv  Detail & Related papers  (2024-10-15T17:23:49Z)
• Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts [103.725112190618]
  This paper introduces Moirai-MoE, using a single input/output projection layer while delegating the modeling of diverse time series patterns to the sparse mixture of experts. Extensive experiments on 39 datasets demonstrate the superiority of Moirai-MoE over existing foundation models in both in-distribution and zero-shot scenarios.
  arXiv  Detail & Related papers  (2024-10-14T13:01:11Z)
• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation [90.53485251837235]
  Time series foundation models excel in zero-shot forecasting, handling diverse tasks without explicit training. GIFT-Eval is a pioneering benchmark aimed at promoting evaluation across diverse datasets. GIFT-Eval encompasses 23 datasets over 144,000 time series and 177 million data points.
  arXiv  Detail & Related papers  (2024-10-14T11:29:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.