用智能体实现结构化数据的自动转换，让大模型更懂数据流程。
Transduction is All You Need for Structured Data Workflows
- 将智能体嵌入数据类型，通过逻辑转换连接不同数据状态。
- 在数据清洗、文本转SQL等任务上表现优异，提升自动化效率。
- 适合需要构建可解释数据流水线的研究与工程人员。
本文提出Agentics，一种基于大语言模型的结构化数据工作流框架。该框架采用以数据为中心的新范式，将智能体嵌入数据类型中，实现结构化状态间的逻辑转换。设计上强调严谨的数据建模，提供声明式语言，使数据类型直接暴露给大模型，数据值通过输入与输出类型间的转换进行组合。我们展示了多种结构化数据工作流任务的实证效果，包括数据清洗、文本到SQL语义解析、特定领域多选题问答以及数据驱动的科学发现任务，验证了该方法的有效性。
原文摘要 · Abstract (English)
This paper introduces Agentics, a functional agentic AI framework for building LLM-based structured data workflow pipelines. Designed for both research and practical applications, Agentics offers a new data-centric paradigm in which agents are embedded within data types, enabling logical transduction between structured states. This design shifts the focus toward principled data modeling, providing a declarative language where data types are directly exposed to large language models and the data values are composed through transductions between input and output types. We present a range of structured data workflow tasks and empirical evidence demonstrating the effectiveness of this approach, including data wrangling, text-to-SQL semantic parsing, and domain-specific multiple-choice question answering, and data-driven scientific discovery tasks.
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。