FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents

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.

2. Document Verification & Archival Data

• Contributing Researchers: 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
• Submission Date: September 28, 2026
• Full Preprint Document: Download Official PDF
• Permanent Archive Record: arXiv:2609.35744v1

3. Academic Citation Reference

Standard Reference (APA Format):

Hoyoung Lee, et al. (2026). FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents. arXiv:2609.35744v1. https://arxiv.org/abs/2609.35744v1

Academic Field: Artificial Intelligence | Document Identifier: arXiv:2609.35744v1

BibTeX Entry:

@article{arxiv_2609.35744v1,
  author    = {Hoyoung Lee and Suyeol Yun and Jack Haverty and Yunju Cho and Meesong Kim and Daekyung Park and Sumin Kim and Jihoon Kwon and Jasmine Jia Geng and Andrew Chin and Yin Luo and Edward Tong and Yu Yu and Zach Golkhou and Minkyu Kim and Igor Halperin and Young Cha and Alejandro Lopez-Lira and Chanyeol Choi and Yongjae Lee},
  title     = {{FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents}},
  journal   = {arXiv preprint arXiv:2609.35744v1},
  year      = {2026},
  url       = {https://arxiv.org/abs/2609.35744v1}
}