Cyber-Zero: Training Cybersecurity Agents without Runtime Paper • 2508.00910 • Published 14 days ago • 7
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning Paper • 2506.24119 • Published Jun 30 • 48
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published Jun 25 • 46
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 Jun 17 • 49
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective Paper • 2506.14965 • Published Jun 17 • 49