SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling Paper • 2512.00466 • Published 11 days ago • 8
GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization Paper • 2511.15705 • Published 21 days ago • 92
DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery Paper • 2508.06960 • Published Aug 9 • 1