作者位次 #5/12ICLR 2026Poster
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Bo Liu · Simon Yu · Zichen Liu · Leon Guertler · Penghui Qi · Daniel Balcells · Mickel Liu · Cheston Tan · Weiyan Shi · Min Lin · Wee Sun Lee · Natasha Jaques