DarwinX: Evolving Agent Harnesses Through Natural Selection Paper • 2608.07545 • Published 25 days ago • 113
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Paper • 2607.22798 • Published Jul 24 • 62
Learning from Language Feedback via Variational Policy Distillation Paper • 2605.15113 • Published May 18 • 13