ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published 4 days ago • 33
CompoWorld: Compositional Environment Scaling for General Agents Paper • 2609.33665 • Published 5 days ago • 36
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published 5 days ago • 32
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents Paper • 2609.33772 • Published 5 days ago • 35
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? Paper • 2609.10226 • Published 23 days ago • 19