NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 5 days ago • 407
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published 18 days ago • 179
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 24 days ago • 275
Demystifying Agent Skills: Why They Work-Until They Don't Paper • 2608.14036 • Published about 1 month ago • 170
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Paper • 2607.15257 • Published Jul 16 • 72