Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published 5 days ago • 32
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning Paper • 2602.01058 • Published Feb 1 • 45
A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence Paper • 2507.21046 • Published Jul 28, 2025 • 86