TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents

TL;DR

TimeSeriesGym is a scalable benchmarking framework designed to evaluate AI agents across diverse time series machine learning engineering challenges, incorporating multiple skills, data sources, and evaluation methods to better reflect real-world ML engineering tasks.

Contribution

We introduce TimeSeriesGym, a comprehensive, scalable benchmark that evaluates AI agents on diverse skills and artifacts, addressing limitations of existing narrow and non-scalable benchmarks.

Findings

Supports evaluation of multiple research artifacts including code and models.

Balances objective and contextual evaluation methods.

Extensible to other data modalities beyond time series.

Abstract

We introduce TimeSeriesGym, a scalable benchmarking framework for evaluating Artificial Intelligence (AI) agents on time series machine learning engineering challenges. Existing benchmarks lack scalability, focus narrowly on model building in well-defined settings, and evaluate only a limited set of research artifacts (e.g., CSV submission files). To make AI agent benchmarking more relevant to the practice of machine learning engineering, our framework scales along two critical dimensions. First, recognizing that effective ML engineering requires a range of diverse skills, TimeSeriesGym incorporates challenges from diverse sources spanning multiple domains and tasks. We design challenges to evaluate both isolated capabilities (including data handling, understanding research repositories, and code translation) and their combinations, and rather than addressing each challenge independently, we develop tools that support designing multiple challenges at scale. Second, we implement evaluation mechanisms for multiple research artifacts, including submission files, code, and models, using both precise numeric measures and more flexible LLM-based evaluation approaches. This dual strategy balances objective assessment with contextual judgment. Although our initial focus is on time series applications, our framework can be readily extended to other data modalities, broadly enhancing the comprehensiveness and practical utility of agentic AI evaluation. We open-source our benchmarking framework to facilitate future research on the ML engineering capabilities of AI agents.