每日文献雷达

2026-07-09

今日入选

• OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System（topic keywords matched; code signal; 16 citations）
• NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions（topic keywords matched; code signal; 1 citations）
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies（topic keywords matched; code signal）
• MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark（topic keywords matched; code signal; 13 citations）
• CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL（topic keywords matched; 157 citations）

1. OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System

• 来源：deepxiv
• 分数：0.5207
• 入选原因：topic keywords matched; code signal; 16 citations
• 摘要：We introduce OneKE, a dockerized schema-guided knowledge extraction system, which can extract knowledge from the Web and raw PDF Books, and support various domains (science, news, etc.). Specifically, we design OneKE wit...
• 链接：https://arxiv.org/abs/2412.20005

2. NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions

• 来源：deepxiv
• 分数：0.4975
• 入选原因：topic keywords matched; code signal; 1 citations
• 摘要：Natural Language to SQL (NL2SQL) technology empowers non-expert users to query relational databases without requiring SQL expertise. While large language models (LLMs) have greatly improved NL2SQL algorithms, their rapid...
• 链接：https://arxiv.org/abs/2604.16493

3. Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies

• 来源：deepxiv
• 分数：0.49
• 入选原因：topic keywords matched; code signal
• 摘要：Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advance...
• 链接：https://arxiv.org/abs/2605.03596

4. MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark

• 来源：deepxiv
• 分数：0.4686
• 入选原因：topic keywords matched; code signal; 13 citations
• 摘要：Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally require expert-level users like data engin...
• 链接：https://arxiv.org/abs/2506.05587

5. CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

• 来源：deepxiv
• 分数：0.46
• 入选原因：topic keywords matched; 157 citations
• 摘要：In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to i...
• 链接：https://arxiv.org/abs/2410.01943