今日 slides：research-radar-2026-09-21

每日文献雷达：2026-09-21

今日自动检索并筛选出 1 篇候选论文，通过结构化深度阅读生成以下分析。

flowchart TB
    subgraph TODAY["今日入选 2026-09-21"]
    P1["BI-Agent and BI-Bench: Towards Automating End-to-E..."]
    end
    TODAY --> BLOG["博客深度阅读"]
    BLOG --> SLIDES["Marp 幻灯片"]
    style TODAY fill:#f0f4ff,stroke:#4a90d9
    style BLOG fill:#d4edda,stroke:#155724
    style SLIDES fill:#e2d9f3,stroke:#6f42c1

今日入选

• BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence（score: 0.5975）

---

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

• 作者：Chuxuan Hu, Yeye He, Penny Zhou, Wee Hyong Tok, Daniel Kang et al.
• 入选原因：topic keywords matched; published this month; code signal
• 来源信息：代码：https://github.com/Hu-Chuxuan/bi-agent | 链接：https://arxiv.org/abs/2609.20886

Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau.

• 摘要：Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building join relationships, before they can (4) answer their business questions. These steps can be complex and time-consuming, making BI challenging. Given the strong capabilities of large language models (LLMs) in working with data, we study their ability to answer BI questions end-to-end, without requiring users to manually perform the tedious preparation steps. To do this, we harvest a large collection of real-world BI projects from public sources, and manually extract pairs of (questions, ground-t…

• 方法·三元组：当前环境未配置 LLM API Key，无法生成结构化三元组分析。GitHub Actions CI 中会使用百炼 API 进行深度阅读，采用公众号 storytelling 风格输出。本地可通过设置 LLM_API_KEY、LLM_BASE_URL、LLM_MODEL 环境变量启用。

• 实验：需确认数据集、指标和 baseline。

• 风险：离线或工具降级时摘要可能不足，不能替代人工精读。

• 后续动作：深读方法和实验设计，建议人工使用 /readpaper 精读

检索说明

• 检索层：arXiv（deepxiv）+ Semantic Scholar + Google Scholar，每日查询轮换，保证论文多样性。
• 阅读层：优先获取 arXiv HTML 全文，使用结构化三元组 + 公众号 storytelling 风格拆解论文逻辑。
• 深度阅读方法论参考 /readpaper 技能。
• 自动分析用于雷达筛选，重要论文仍需人工复核。