每日文献雷达

2026-08-13

今日入选

• AgenticDataBench: A Comprehensive Benchmark for Data Agents（topic keywords matched; published this month; code signal）
• DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents（topic keywords matched; published this month）
• LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities（topic keywords matched; code signal; 291 citations）

1. AgenticDataBench: A Comprehensive Benchmark for Data Agents

        - **来源**：deepxiv
        - **分数**：0.5975
        - **入选原因**：topic keywords matched; published this month; code signal
        - **摘要**：Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process is essential to reducing labor-intensive efforts for data scientists and enabling scalable data-dri...

• 链接：https://arxiv.org/abs/2607.01647

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>
  

2. DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents

        - **来源**：deepxiv
        - **分数**：0.5175
        - **入选原因**：topic keywords matched; published this month
        - **摘要**：LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation and production operations: live-environment fidelity (multi-turn read-write interaction with a running database); observation-space...

• 链接：https://arxiv.org/abs/2607.22165

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>
  

3. LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities

        - **来源**：deepxiv
        - **分数**：0.4075
        - **入选原因**：topic keywords matched; code signal; 291 citations
        - **摘要**：This paper presents an exhaustive quantitative and qualitative evaluation of Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning. We engage in experiments across eight diverse datasets, focusing on four representative tasks encompassing entity and rel...

• 链接：https://arxiv.org/abs/2305.13168

        <div style="margin-top: 2rem; padding: 1rem; border-left: 3px solid #4a90d9; font-size: 0.9rem; opacity: 0.85;">
        完整深度阅读见博客文章，使用结构化三元组方法拆解论文逻辑。
        </div>