MIT Releases FinanceGym, the Largest Finance-Agent Dataset with 59K+ Samples

MIT_CSAIL · x · 2026-08-25

MIT CSAIL researchers have released "FinanceGym," the largest finance-agent dataset to date, featuring over 59,000 samples across 37 roles and 40 apps/sites.

The data can be used for Reinforcement Finetuning or Supervised Finetuning of agentic models. It contains human-demonstrated trajectories with thinking traces, designed to teach agents financial work rather than just financial knowledge. Tests show that even Kimi K3 and Qwen 3.8 Max failed its test set.

Related event: MIT Releases FinanceGym, Largest Finance Agent Dataset; Even Top Models Fail(4 posts)→

Original post →

More from coding & agent

coding & agent channel →