Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format?
Abstract page for arXiv paper 2610.20639: Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format?
arXiv.org
Abstract page for arXiv paper 2610.20639: Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format?
arXiv.org