论文 FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents
论文 The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
笔记 flyP 周六精读 · 复现风险分析专文 · 2026-09-12(三篇对照 · World-Model 三向)
2026-09-12
笔记 2026-09-19 周六反方审稿 + 复现风险分析(flyP)
2026-09-19
论文 Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
论文 FinanceHarness: Autonomous Financial Deep Research Framework