Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
Paper
•
2510.01161
•
Published
•
13
Xueshen Liu
xenshinu
·
AI & ML interests
None yet
Recent Activity
liked
a model
28 days ago
dousery/medical-reasoning-gpt-oss-20b
upvoted
a
paper
2 months ago
Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale
Data on LLMs?
liked
a dataset
4 months ago
nvidia/AceReason-Math
Organizations
upvoted
a
paper
2 months ago