# In-Browser Agents for Search Assistance

arXiv: https://arxiv.org/abs/2601.09928 · HTML: https://mlsanity.com/paper/2601.09928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 14 of 14)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [USimAgent: Large Language Models for Simulating Search Users](https://mlsanity.com/paper/2403.09142/) (2024)
- [A Survey of Small Language Models](https://mlsanity.com/paper/2410.20011/) (2024)
- [Active learning for data streams: a survey](https://mlsanity.com/paper/2302.08893/) (2023)
- [Multi-Agent Large Language Models for Conversational Task-Solving](https://mlsanity.com/paper/2410.22932/) (2024)
- [WebLLM: A High-Performance In-Browser LLM Inference Engine](https://mlsanity.com/paper/2412.15803/) (2024)
- [Anatomizing Deep Learning Inference in Web Browsers](https://mlsanity.com/paper/2402.05981/) (2024)
- [WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale](https://mlsanity.com/paper/2510.16252/) (2025)
- [Lookup or Exploratory: What is Your Search Intent?](https://mlsanity.com/paper/2110.04640/) (2021)
- [BMLP: Behavior-aware MLP for Heterogeneous Sequential Recommendation](https://mlsanity.com/paper/2402.12733/) (2024)
- [E-commerce Webpage Recommendation Scheme Base on Semantic Mining and Neural Networks](https://mlsanity.com/paper/2409.07033/) (2024)

## Abstract (arXiv)

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.