Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play Paper • 2509.25541 • Published Sep 29 • 140
Mem-α: Learning Memory Construction via Reinforcement Learning Paper • 2509.25911 • Published Sep 30 • 14
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning Paper • 2509.22576 • Published Sep 26 • 134
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance Paper • 2506.06444 • Published Jun 6 • 73
