From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search Paper • 2607.24280 • Published 2 days ago • 68
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators Paper • 2607.20465 • Published May 19 • 49
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Paper • 2607.21553 • Published 6 days ago • 37
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published 13 days ago • 103
nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 Text Generation • 45B • Updated 22 days ago • 65.8k • 125
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe Paper • 2607.03451 • Published 26 days ago • 33
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments Paper • 2607.05155 • Published 23 days ago • 18
Qwen-AgentWorld: Language World Models for General Agents Paper • 2606.24597 • Published Jun 23 • 153