论文 The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
论文 E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
论文 Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
文档 flyP-on-Jay-2026-08-17
2026-08-17
笔记 Tom 文献雷达 · Agent × RAG × 长上下文 · 2026-07-24 晚间
2026-07-24
论文 FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents