FinanceHarness：自动化金融深度研究框架
原标题：FinanceHarness: Autonomous Financial Deep Research Framework
AI 摘要
FinanceHarness 是一个用于金融深度研究的自动化框架，集成了金融工具、工作流和奖励模型，并提出了 FinanceGym 基准，包含基于论文的研究问题和评分标准。专家验证通过率为 82%，而领先的 LLM 和代理在评分标准上得分低于 40%，表明该基准具有挑战性。使用相同的开放权重骨干，FinanceHarness 将整体评分从 25.3% 提升至 32.4%。该框架已在 GitHub 上开源。
正文节选
FinanceHarness: Autonomous Financial Deep Research Framework Abstract Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products. However, most deep research systems write general-purpose reports, which are inadequate for financial deep research. Financial research demands specialized knowledge to analyze historical patterns and forecast upcoming events. Automating financial deep research therefore requires both a layered harness t