See2Think: Do Multimodal Models Really Use Intermediate Visual States? Paper • 2607.26769 • Published 7 days ago • 24
AREX: Towards a Recursively Self-Improving Agent for Deep Research Paper • 2607.21461 • Published 13 days ago • 151
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Paper • 2605.29707 • Published May 28 • 152
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253