MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory Paper • 2605.15128 • Published May 14 • 65
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published Apr 24 • 158
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play Paper • 2509.25541 • Published Sep 29, 2025 • 142
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning Paper • 2509.22576 • Published Sep 26, 2025 • 137
