SWE-Next: Scalable Real-World Software Engineering Tasks for Agents Paper • 2603.20691 • Published 21 days ago • 10
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction Paper • 2602.13294 • Published Feb 9 • 13
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction Paper • 2602.13294 • Published Feb 9 • 13
VisCoder2: Building Multi-Language Visualization Coding Agents Paper • 2510.23642 • Published Oct 24, 2025 • 22