Paper Detail
Kaisen Yang, Zheng Jiang, Yuzhao Peng, Houde Qian, Boshi Zhang, Youjie Zheng, Shijin Hong, Qingle Liu, Ruoyu Han, Bohan Lyu, Bingxiang He, Eren Cai, Calvin Xiao, Qinhuai Na
Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalable but under-exploited source of reusable browser skills. We argue that the bottleneck for browser agents is decision-making under incomplete information rather than low-level operation, and that the priors agents lack are already implicit in human interaction traces. We therefore study scalable behavior cloning for browser agents via skill distillation, converting user interaction trajectories into compact natural-language skills that agents can read, retrieve, reuse, and compose directly. We further organize the distilled skills into a skill graph so that growth proceeds through consolidation rather than unbounded accumulation. This suggests that the scalability of browser agents may come less from manually designed tasks and more from the collective skills already expressed by internet users. Our project is available at: https://lab.einsia.ai/browserbc/.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{yang2026scalable,
title = {Scalable Behaviour Cloning on Browser Using via Skill Distillation},
author = {Kaisen Yang and Zheng Jiang and Yuzhao Peng and Houde Qian and Boshi Zhang and Youjie Zheng and Shijin Hong and Qingle Liu and Ruoyu Han and Bohan Lyu and Bingxiang He and Eren Cai and Calvin Xiao and Qinhuai Na},
year = {2026},
abstract = {Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalable but under-exploited source of reusable browser skills. We argue that the bottleneck for browser agents is decision-making under incomplete information rather than low-level operation, and that the priors agents lack are already implicit in human interaction traces. We therefor},
url = {https://arxiv.org/abs/2606.32014},
keywords = {cs.CL},
eprint = {2606.32014},
archiveprefix = {arXiv},
}
{}