DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents Paper • 2608.18524 • Published 30 days ago • 105
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published 23 days ago • 272
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published 22 days ago • 146