Guardado en:
Detalles Bibliográficos
Autores principales: Nam, Jaehyun, Yoon, Jinsung, Chen, Jiefeng, Sinha, Raj, Shin, Jinwoo, Pfister, Tomas
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.21825
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914345790734336
author Nam, Jaehyun
Yoon, Jinsung
Chen, Jiefeng
Sinha, Raj
Shin, Jinwoo
Pfister, Tomas
author_facet Nam, Jaehyun
Yoon, Jinsung
Chen, Jiefeng
Sinha, Raj
Shin, Jinwoo
Pfister, Tomas
contents While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring multiple sources and synthesizing open-ended insights. In this paper, we introduce DS-STAR, a specialized agent to bridge this gap. Unlike prior approaches, DS-STAR is designed to (1) seamlessly process and integrate data across diverse, heterogeneous formats, and (2) move beyond simple QA to generate comprehensive research reports for open-ended queries. Extensive evaluation shows that DS-STAR achieves state-of-the-art performance on four benchmarks: DABStep, DABStep-Research, KramaBench, and DA-Code. Most notably, it significantly outperforms existing baseline models especially in hard-level QA tasks requiring multi-file processing, and generates high-quality data science reports that are preferred over the best baseline model in over 88% of cases.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21825
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries
Nam, Jaehyun
Yoon, Jinsung
Chen, Jiefeng
Sinha, Raj
Shin, Jinwoo
Pfister, Tomas
Artificial Intelligence
While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring multiple sources and synthesizing open-ended insights. In this paper, we introduce DS-STAR, a specialized agent to bridge this gap. Unlike prior approaches, DS-STAR is designed to (1) seamlessly process and integrate data across diverse, heterogeneous formats, and (2) move beyond simple QA to generate comprehensive research reports for open-ended queries. Extensive evaluation shows that DS-STAR achieves state-of-the-art performance on four benchmarks: DABStep, DABStep-Research, KramaBench, and DA-Code. Most notably, it significantly outperforms existing baseline models especially in hard-level QA tasks requiring multi-file processing, and generates high-quality data science reports that are preferred over the best baseline model in over 88% of cases.
title DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries
topic Artificial Intelligence
url https://arxiv.org/abs/2509.21825