VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published 14 days ago • 167
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published 16 days ago • 169
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies Paper • 2602.09877 • Published 14 days ago • 192
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Paper • 2602.08222 • Published 16 days ago • 268
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Paper • 2602.08222 • Published 16 days ago • 268