Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Ximing Lu , David Acuna , Jaehun Jung , Jian Hu , Di Zhang , Shizhe Diao , Yunheng Zou , Shaokun Zhang , Brandon Cui , Mingjie Liu , Hyunwoo Kim , Prithviraj Ammanabrolu , Jan Kautz , Yi Dong , Yejin Choi

January, 2026

PDF Dataset

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Ximing Lu , David Acuna , Jaehun Jung , Jian Hu , Di Zhang , Shizhe Diao , Yunheng Zou , Shaokun Zhang , Brandon Cui , Mingjie Liu , Hyunwoo Kim , Prithviraj Ammanabrolu , Jan Kautz , Yi Dong , Yejin Choi

January, 2026

PDF Dataset

Abstract

In International Conference on Machine Learning (ICML), 2026

Type

Conference paper

Publication

ICML 2026