Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes

v1v2 (latest)

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes

26 January 2026

Amrith Setlur

Zijian Wang

Andrew Cohen

Paria Rashidinejad

Sang Michael Xie

ArXiv (abs)PDF HTML

Papers citing "Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes"

0 / 0 papers shown

No papers found