vix.ing
·
top
·
new
·
best
·
stats
·
spec
Yibo Xie
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning
2026/08/02 by
Wenhao Zhang
,
Yibo Xie
,
Rui Wang
+9
Computer Science
·
#cs.AI
#cs.LG