CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling

Excerpt

arXiv:2610.06829v1 Announce Type: cross Abstract: Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while frontier-language-model judges are too expensive to call at every step and cannot be assumed available at deployment. We introduce CLIFT, a training and test-time scaling method built around conformal self-verification. Durin