GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 16 days ago • 293
AgentSWE: Can Coding Agents Build the Agent You Actually Want? Paper • 2610.13361 • Published 7 days ago • 217
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published Aug 27 • 62