RunningTab: Direct Workspace Interaction with Environment-Side Tabs Paper • 2610.10444 • Published 7 days ago • 40
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents Paper • 2610.05140 • Published 10 days ago • 45
Follow the Entities: A Corpus Map for Agentic Search Paper • 2609.37226 • Published 15 days ago • 100