David Acuna
Home
Publications
MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis
Ximing Lu
,
Aviral Kumar
,
Jan Kautz
,
Yejin Choi
,
David Acuna
October, 2026
PDF
MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis
Ximing Lu
,
Aviral Kumar
,
Jan Kautz
,
Yejin Choi
,
David Acuna
October, 2026
PDF
Abstract
arXiv preprint, 2026
Type
Manuscript
Cite
×