SOURCE-LINKED INTELLIGENCE

When and What to Teach: Budget-Aware Online Adaptation for Web Agents

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Web agents have achieved significant success in automating complex internet tasks but deploying them in real-world environments requires continuous online adaptation. Given that deploying powerful proprietary models remains commercially cost-prohibitive, practitioners must rely on lightweight local models that evolve post-deployment via online teaching from a stronger teacher. However, standard interactive feedback imposes prohibitive costs. We show that conventional trajectory-level preference optimization wastes budget on both unresolvable episodes and redundant execution turns. To resolve t

Read original source ↗ Open in workspace

recordType

paper

region

Global