Cite
Notes
Only stored in your browser.
Attribution
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
arXiv 2025
from 1 papers
Bo Liu
researcher
Cheston Tan
Leon Guertler
Mickel Liu
Min Lin
Natasha Jaques
Penghui Qi
Simon Yu
Wee Sun Lee
Weiyan Shi