-
spiral-rl/Spiral-Qwen3-4B
Text Generation • 4B • Updated • 105 • 4 -
spiral-rl/Spiral-DeepSeek-R1-Distill-Qwen-7B
Text Generation • 8B • Updated • 2 • 2 -
spiral-rl/Spiral-Kuhn-Poker-Qwen3-32B-SFT
Viewer • Updated • 25.5k • 21 -
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper • 2506.24119 • Published • 51
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
spiral-rl/Spiral-Qwen3-4B
Text Generation • 4B • Updated • 105 • 4 -
spiral-rl/Spiral-DeepSeek-R1-Distill-Qwen-7B
Text Generation • 8B • Updated • 2 • 2 -
spiral-rl/Spiral-Kuhn-Poker-Qwen3-32B-SFT
Viewer • Updated • 25.5k • 21 -
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper • 2506.24119 • Published • 51
models 74
spiral-rl/qwen3-8b-0627-games-blend-iter287
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter271
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter255
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter239
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter223
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter207
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter191
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter175
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter159
8B • Updated
spiral-rl/qwen3-8b-0627-games-blend-iter143
8B • Updated