StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Paper • 2608.17800 • Published Aug 18 • 140
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Paper • 2610.01762 • Published 21 days ago • 239
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence Paper • 2609.35432 • Published 24 days ago • 113
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 495
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published 30 days ago • 165