SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation Paper • 2608.02287 • Published 3 days ago • 28
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces Paper • 2604.05172 • Published Apr 6 • 25
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks Paper • 2602.12670 • Published Feb 13 • 65