AREX: Towards a Recursively Self-Improving Agent for Deep Research Paper • 2607.21461 • Published 15 days ago • 151
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published 25 days ago • 84
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models Paper • 2605.30161 • Published May 28 • 60
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild Paper • 2605.27882 • Published May 27 • 17
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433