CompoWorld: Compositional Environment Scaling for General Agents Paper • 2609.33665 • Published 15 days ago • 41
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 13 days ago • 137
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published 12 days ago • 64
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published 12 days ago • 64