SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning Paper • 2506.24119 • Published 9 days ago • 43
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published 14 days ago • 42
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models Paper • 2411.08733 • Published Nov 13, 2024 • 1
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective Paper • 2506.14965 • Published 22 days ago • 47
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective Paper • 2506.14965 • Published 22 days ago • 47