---
title: "通过技能蒸馏实现浏览器上的可扩展行为克隆"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2606.32014v1"
permalink: "https://feed.astralor.com/items/itm_acd9bcf147f53f4f567961f4"
published: "2026-06-30T17:46:23.000Z"
score: 53
channel: "ai"
tags: ["可扩展性","技能图","技能蒸馏","浏览器智能体","行为克隆"]
---

# 通过技能蒸馏实现浏览器上的可扩展行为克隆

## 速览

本文提出通过技能蒸馏将用户浏览器交互轨迹转化为自然语言技能，使浏览器智能体能够读取、检索、复用和组合这些技能，从而克服传统行为克隆在决策不完全信息下的瓶颈。作者进一步将蒸馏出的技能组织成技能图，实现通过整合而非无限积累的方式扩展技能库，表明浏览器智能体的可扩展性可能更多来自互联网用户的集体技能而非人工设计任务。

## 关键点

- 提出技能蒸馏方法，从人类浏览器交互轨迹中提取自然语言技能。
- 将技能组织为技能图，支持整合式增长而非无限累积。
- 展示了智能体可直接利用用户已有的集体技能进行决策。

## 全文

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/.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_acd9bcf147f53f4f567961f4