paper-with-me

홈 › Papers

Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel

2026-03-12 · Aadyaa Maddi, Prakhar Naval, Deepti Mande, Shane Duan, Muckai Girish, Vyas Sekar arxiv

Across many domains (e.g., IoT, observability, telecommunications, cybersecurity), there is an emerging adoption of conversational data analysis agents that enable users to "talk to your data" to extract insights. Such data analysis agents operate on timeseries data models; e.g., measurements from sensors or events monitoring user clicks and actions in product analytics. We evaluate 6 popular data analysis agents (both open-source and proprietary) on domain-specific data and query types, and find that they fail on stateful and incident-specific queries. We observe two key expressivity gaps in existing evals: domain-customized datasets and domain-specific query types. To enable practitioners in such domains to generate customized and expressive evals for such timeseries data agents, we present AgentFuel. AgentFuel helps domain experts quickly create customized evals to perform end-to-end functional tests. We show that AgentFuel's benchmarks expose key directions for improvement in existing data agent frameworks. We also present anecdotal evidence that using AgentFuel can improve agent performance (e.g., with GEPA). AgentFuel benchmarks are available at https://huggingface.co/datasets/RockfishData/TimeSeriesAgentEvals.

📄 PDF Abstract BibTeX arXiv:2603.12483

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale

2026-04-11 · Malgorzata Gwiazda, Yifu Cai, Mononito Goswami, Arjun Choudhry 외 arxiv

Large Language Models (LLMs) have shown promising performance in time series modeling tasks, but do they truly understand time series data? While multiple benchmarks have been proposed to answer this fundamental question…

GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization

2026-03-26 · Zhangyu Jin, Maksim Siniukov, Deuksin Kwon, Ashutosh Chaubey 외 arxiv

Generating realistic 3D head motion for dyadic interactions is a significant challenge in virtual human synthesis. While recent methods achieve impressive results with speaking heads, they frequently suffer from the `Reg…

xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods

2025-02-05 · Pratinav Seth, Yashwardhan Rathore, Neeraj Kumar Singh, Chintan Chitroda 외

The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale behind predictions. This lack of transpa…

Benchmarking

Measuring all the noises of LLM Evals

2025-12-24 · Sida Wang arxiv

Separating signal from noise is central to experiments. Applying well-established statistical methods effectively to LLM evals requires consideration of their unique noise characteristics. We clearly define and measure t…

AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting

2023-08-10 · Oleksandr Shchur, Caner Turkmen, Nick Erickson, Huibin Shen 외

We introduce AutoGluon-TimeSeries - an open-source AutoML library for probabilistic time series forecasting. Focused on ease of use and robustness, AutoGluon-TimeSeries enables users to generate accurate point and quanti…

AutoMLPhilosophyProbabilistic Time Series ForecastingTime Series+1