EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents Paper • 2610.13021 • Published 10 days ago • 74
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments Paper • 2610.12611 • Published 11 days ago • 114
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards Paper • 2610.18868 • Published 6 days ago • 111
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models Paper • 2609.05533 • Published Sep 2 • 16
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? Paper • 2609.00787 • Published Sep 1 • 19
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? Paper • 2609.10226 • Published Sep 9 • 18
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents Paper • 2609.08149 • Published Sep 8 • 27
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks Paper • 2609.11042 • Published Sep 10 • 66