让大模型生成可编辑的数据流水线，告别一次性脚本。
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
- 用逐步修改的有类型图结构替代自由编码，实现持久化流水线。
- 在12个任务上达到93.3%成功率，成本比普通代码生成低72.5%。
- 适合需要可维护数据管道的研发人员，尤其依赖隐含流程知识的任务。
大型语言模型（LLMs）正被用于自动化数据处理流程，但传统代码代理生成的脚本难以作为持久、可编辑的平台资产。我们称此为“NL2Pipeline缺口”。为此，提出 extsc{DataFlow-Harness} 平台，引导 LLM 代理通过有类型、增量式修改构建平台原生的有向无环图（DAG），而非自由形式脚本。该平台结合 extsc{DataFlow-Skills} 提供过程指导、模型上下文协议（MCP）层暴露实时算子注册表与当前流水线状态，并通过 extsc{DataFlow-WebUI} 实现对话式编写与可视化 DAG 编辑同步。在12项数据工程基准测试中， extsc{DataFlow-Harness} 达到93.3%的端到端通过率；相比原始 Claude Code，其测量成本降低72.5%，生成延迟减少49.9%；通过率仅比上下文感知的 Claude Code 基线低0.9个百分点，但成本低42.8%。任务级分析表明，当构建依赖隐含流程知识时，Skills 最为有效。结果表明，实时平台嵌入可生成可靠、持久且可编辑的工作流，性能接近脚本生成基线，同时显著降低构建成本与延迟。
原文摘要 · Abstract (English)
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 LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer that exposes the live operator registry and current pipeline state, and \textsc{DataFlow-WebUI}, which synchronizes conversational authoring with a visual DAG editor. On a 12-task data-engineering benchmark, \textsc{DataFlow-Harness} achieves a 93.3\% observed end-to-end pass rate. Relative to Vanilla Claude Code, it reduces measured monetary cost by 72.5\% and generation latency by 49.9\%; its observed pass rate is within 0.9 percentage points of the Context-Aware Claude Code baseline while its cost is 42.8\% lower. Per-task analysis indicates that Skills are most useful when construction depends on implicit procedural knowledge. These results show that live platform grounding can produce persistent, editable workflow artifacts with an observed reliability close to script-generation baselines and with lower measured construction cost and latency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。