CocoaBench: Evaluating Unified Digital Agents in the Wild Paper • 2604.11201 • Published 2 days ago • 28
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 6 days ago • 252
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published 9 days ago • 35
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning Paper • 2603.12698 • Published Mar 13 • 1
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation Paper • 2603.19220 • Published 26 days ago • 66
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 28 days ago • 94
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 28 days ago • 94
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 28 days ago • 94