用多智能体协作提升数据洞察力，解决知识不足与代码错误问题
DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning
- 引入外部知识检索、多角色辩论和多路径推理三重机制
- 在InsightBench上各难度下均优于现有方法，表现全面领先
- 适合需要深度分析与高可靠性的企业级数据分析场景
在数据驱动时代，全自动端到端数据洞察发现对组织决策至关重要。随着大语言模型（LLMs）的发展，基于LLM的智能体成为自动化数据分析与洞察发现的有前景范式。然而，现有数据洞察智能体仍存在三大局限：(1) 领域知识利用不足，(2) 分析深度浅，(3) 洞察生成中代码易出错。为此，我们提出DataSage——一种新型多智能体框架，包含三项创新：外部知识检索以丰富分析上下文，多角色辩论机制模拟多元分析视角并深化分析深度，多路径推理提升生成代码与洞察的准确性。在InsightBench上的大量实验表明，DataSage在所有难度级别上均持续优于现有数据洞察智能体，为自动化数据洞察发现提供了有效解决方案。
原文摘要 · Abstract (English)
In today's data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in making effective decisions. With the rapid advancement of large language models (LLMs), LLM-driven agents have emerged as a promising paradigm for automating data analysis and insight discovery. However, existing data insight agents remain limited in several key aspects, often failing to deliver satisfactory results due to: (1) insufficient utilization of domain knowledge, (2) shallow analytical depth, and (3) error-prone code generation during insight generation. To address these issues, we propose DataSage, a novel multi-agent framework that incorporates three innovative features including external knowledge retrieval to enrich the analytical context, a multi-role debating mechanism to simulate diverse analytical perspectives and deepen analytical depth, and multi-path reasoning to improve the accuracy of the generated code and insights. Extensive experiments on InsightBench demonstrate that DataSage consistently outperforms existing data insight agents across all difficulty levels, offering an effective solution for automated data insight discovery.
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。