PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas Paper • 2610.22990 • Published 15 days ago • 15
Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops Paper • 2610.18579 • Published 18 days ago • 9
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure Paper • 2609.26550 • Published Sep 22 • 44