Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition Paper • 2610.28578 • Published 1 day ago • 58
Does Learning Protein Folding Generalize to Broader Reasoning? Paper • 2609.38879 • Published 22 days ago • 64
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Paper • 2609.18708 • Published Sep 16 • 85