Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2510.13786
Cited By
The Art of Scaling Reinforcement Learning Compute for LLMs
15 October 2025
Devvrit Khatri
Lovish Madaan
Rishabh Tiwari
Rachit Bansal
Sai Surya Duvvuri
Manzil Zaheer
Inderjit Dhillon
David Brandfonbrener
Rishabh Agarwal
OffRL
Re-assign community
ArXiv (abs)
PDF
HTML
HuggingFace (27 upvotes)
Github (967★)
Papers citing
"The Art of Scaling Reinforcement Learning Compute for LLMs"
1 / 1 papers shown
Title
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
Christos Thrampoulidis
Sadegh Mahdavi
Wenlong Deng
OffRL
32
0
0
27 Oct 2025
1
