FinAutoRubric：面向金融研究智能体评测的专家引导自动评分标准生成
FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents
FinAutoRubric 让专家只提供可复用的评测指引，由智能体与代码完成针对具体查询的评分标准生成、审查与验证，失败案例升级给人工处理。在三个专家编写的金融基准上，其评分标准与专家评分的接近程度达到所评估生成器中最强水平，并在更多标准上给出专家评分标准的期望值。团队同时发布 100 条查询的 FinAutoRubric Benchmark，覆盖 78 个任务和八类资产。
Authors:Hoyoung Lee, Suyeol Yun, Jack Haverty, Yunju Cho, Meesong Kim, Daekyung Park, Sumin Kim, Jihoon Kwon, Jasmine Jia Geng, Andrew Chin, Yin Luo, Edward Tong, Yu Yu, Zach Golkhou, Minkyu Kim, Igor Halperin, Young Cha, Alejandro Lopez-Lira, Chanyeol Choi, Yongjae Lee
Abstract:Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify reusable evaluation guidance, while agents and code carry out query-specific rubric generation, review, and validation. This expert guidance governs every agent, as prompts and as rules that code enforces, and a Task Bank of reusable criteria carries it across tasks. In long-horizon loops that follow the expert guidance, a writer agent researches every expected value and a reviewer agent verifies it, and failures escalate to a human. On three expert-authored finance benchmarks, its rubrics track expert scoring as closely as the strongest evaluated generator while stating the expert rubric's expected value for more criteria, their scores agree with human grading, and in-house analysts prefer them in a blind review. The released 100-query FinAutoRubric Benchmark, built from in-house analysts' key questions across 78 tasks and eight asset classes, shows that rubrics from an earlier model generation still leave headroom for a later one.
| Comments: | preprint |
| Subjects: | Artificial Intelligence (cs.AI); Computational Finance (q-fin.CP) |
| Cite as: | arXiv:2609.35744 [cs.AI] |
| (or arXiv:2609.35744v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.35744 arXiv-issued DOI via DataCite |
Submission history
From: Hoyoung Lee [view email]
[v1]
Mon, 28 Sep 2026 17:55:06 UTC (659 KB)
[v2]
Mon, 26 Oct 2026 16:04:01 UTC (829 KB)
来源：arXiv cs.AI · arxiv.org