SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper
•
2506.24119
•
Published
•
43
Xiaohan Fu
x5fu
AI & ML interests
Security and Safety
Recent Activity
authored
a paper
about 1 month ago
Training Language Models to Generate Quality Code with Program Analysis
Feedback
upvoted
a
paper
about 1 month ago
Training Language Models to Generate Quality Code with Program Analysis
Feedback
Organizations
None yet
upvoted
a
paper
12 days ago