In-Browser Agents for Search Assistance

2026-01-14

AI Summary

This work proposes the first fully client-side hybrid-architecture search agent designed to deliver intelligent search assistance while preserving user privacy. The system integrates an adaptive probabilistic behavioral model with an embedded small language model (SLM), leveraging a user feedback–driven policy learning mechanism to dynamically generate context-aware, personalized search suggestions. A three-week longitudinal user study involving 18 participants demonstrates that the approach significantly improves search efficiency and effectively adapts to individual user behaviors. Critically, all sensitive data remain strictly on-device, ensuring robust privacy protection without compromising personalization capabilities.

Technology Category

• Search and Optimization: Learning to Search
• Humans and AI: Intelligent User Interfaces
• Machine Learning: Privacy

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

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.

Problem

• privacy
• web search
• AI assistance
• user data control
• in-browser AI

Innovation

• in-browser AI
• privacy-preserving search
• Small Language Model
• adaptive probabilistic model
• client-side architecture