跳到正文
Ant Ling· @AntLingAGI · X·· 2026-09-05AI 评分31
AI 导读

自发布以来,FinFIRST 引起了广泛关注。它与金融专家共同构建,使用原子评分细则来评估回答和证据,包括智能体如何搜索、处理实时真实世界任务、整合来源、选择可靠证据、进行计算,并让结果易于验证。🧵

正文

Since its release, FinFIRST has drawn a lot of interest. Built with finance experts, it uses atomic rubrics to assess both answers and evidence, including how agents search, handle timely real world tasks, combine sources, choose reliable evidence, calculate and make results easy to verify. 🧵

来源:Ant Ling · x.com