CompoWorld: Compositional Environment Scaling for General Agents Paper • 2609.33665 • Published 23 days ago • 42
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 21 days ago • 135
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published 20 days ago • 42
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published 20 days ago • 42