HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 5 days ago • 238
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published 11 days ago • 179
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 17 days ago • 274
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published 20 days ago • 151