E2080 - DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Published: July 23, 2026
Duration: 19:21
🤗 Upvotes: 122 | cs.SE, cs.AI
Authors:
Runming He, Zhen Hao Wong, Hao Liang, Zimo Meng, Chengyu Shen, Xiaochen Ma, Wentao Zhang
Title:
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Arxiv:
http://arxiv.org/abs/2607.16617v1
Abstract:
Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \textit{NL2Pipeline gap}. To bridge it, we introduce \textsc{DataFlow-Harness}, a platform that guides an...