Paper page - CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?

Source: https://huggingface.co/papers/2606.15300

Abstract

Advanced agents struggle to effectively integrate data discovery with code execution in data-intensive environments, revealing a significant gap in current agentic capabilities.

Advanced agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation benchmarks that capture the complexity of real-world development. Such environments typically involve both complex code and large-scale data (i.e., file system). However, existing benchmarks usually evaluate code-centric ordata-centric capabilitiesin isolation, leaving a clear gap with real development scenarios. In this paper, we bridge this gap by introducing CODA-BENCH, the first benchmark to jointly evaluate code and data intelligence in adata-intensive environment. We construct a data-intensive Linux sandbox based on the Kaggle ecosystem (containing hundreds of datasets), where agents must actively explore complex file hierarchies to identify relevant resources and generate code for data-driven analytical tasks. CODA-BENCH comprises 1,009 tasks spanning 31 communities, with each task environment containing an average of 980 files, simulating realistic data scale and noise. Evaluations of advanced agents reveal that even top-performing systems struggle to effectively integratedata discoverywithcode execution, achieving a success rate of only 61.1%. These results highlight a substantial gap in current agentic capabilities for data-intensive tasks and point to promising directions for future research.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2606\.15300

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.15300 in a model README.md to link it from this page.

Datasets citing this paper1

#### RUC-DataLab/CoDA-Bench Viewer• Updatedabout 8 hours ago • 1.13k • 123 • 1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.15300 in a Space README.md to link it from this page.

Collections including this paper2