浏览器内运行的AI助手，保护隐私还能提升搜索效率
In-Browser Agents for Search Assistance
- 在浏览器本地运行混合模型，不上传用户数据
- 18人三周实验显示搜索效率明显提升
- 适合注重隐私的普通用户和开发者
网页搜索中对复杂AI辅助的需求与用户数据隐私之间存在根本矛盾。当前集中式模型需将敏感浏览数据传至外部服务，限制了用户控制权。本文提出一种浏览器插件，提供完全在客户端运行的替代方案。采用混合架构，包含：(1) 基于直接反馈学习用户行为策略的自适应概率模型；(2) 在浏览器中运行的轻量语言模型（SLM），由概率模型提供上下文支撑以生成智能建议。通过为期三周的纵向用户研究（18名参与者）评估该方法，结果表明该隐私保护方案能有效适配个体用户行为，显著提升搜索效率。本工作证明，在不牺牲用户隐私或数据控制的前提下，实现高级别AI辅助是可行的。
原文摘要 · Abstract (English)
A fundamental tension exists between the demand for sophisticated AI assistance in web search and the need for user data privacy. Current centralized models require users to transmit sensitive browsing data to external services, which limits user control. In this paper, we present a browser extension that provides a viable in-browser alternative. We introduce a hybrid architecture that functions entirely on the client side, combining two components: (1) an adaptive probabilistic model that learns a user's behavioral policy from direct feedback, and (2) a Small Language Model (SLM), running in the browser, which is grounded by the probabilistic model to generate context-aware suggestions. To evaluate this approach, we conducted a three-week longitudinal user study with 18 participants. Our results show that this privacy-preserving approach is highly effective at adapting to individual user behavior, leading to measurably improved search efficiency. This work demonstrates that sophisticated AI assistance is achievable without compromising user privacy or data control.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。