Scalable browser behavior cloning distills reusable skills from human traces
arXiv·medium signal
The paper argues the real bottleneck for browser agents is decision-making under incomplete information, not low-level clicking, and that the missing priors are already implicit in human browsing traces. It proposes skill distillation to convert large-scale human interaction traces into reusable browser skills via behavior cloning. Relevant for anyone building web agents who has interaction logs but weak planning priors.