FinSkillBench: Evaluating AI Agents and Domain Skills for Investment Management

By Jermyn Zhen Yong Bek, Zhuang Qiang Bok, Zhongtian Sun

Published 2026-06-09

Everscope rating

1409.1

Relevance to quantitative trading

8 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: FinSkillBench Factorial Agentic Evaluation Protocol. Problem types: Portfolio Optimization, Risk Management, Natural Language Processing, Structured Prediction, Optimization, Ranking, Information Extraction, Multi-task Learning.

arXiv:2608.18099 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.