GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution Paper • 2610.00948 • Published 7 days ago • 11
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization Paper • 2609.11682 • Published 28 days ago • 46
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation Paper • 2608.04419 • Published Aug 5 • 30