List your company

ResearchFormerly WizWand

Hangman

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning

Hangman OOD-1

6.84Cumulative Reward

3

In-context adaptation

Hangman

6.48Cumulative Reward

3

Reinforcement Learning

Hangman (OOD-2)

5.65Cumulative Reward

2