DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis 事件

DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis arXiv:2605.02503v3 Announce Type: replace Abstract: Autonomous data analysis agents are increasingly expected to conduct exploratory analysis with limited human guidance about data. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data sources, explicit data schemas, or cleaned data, thereby understating the exploratory burden. To evaluate this realistic e