WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492883" target="_blank" >RIV/00216208:11320/24:10492883 - isvavai.cz</a>

Result on the web

<a href="https://openreview.net/forum?id=mUSPhG4uDW" target="_blank" >https://openreview.net/forum?id=mUSPhG4uDW</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2402.05930" target="_blank" >10.48550/arXiv.2402.05930</a>

Result language

angličtina

Original language name

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Original language description

We propose the problem of conversational web navigation, where a digital agent controls a web browser and follows user instructions to solve realworld tasks in a multi-turn dialogue fashion. To support this problem, we introduce WebLINX - a large-scale benchmark of 100K interactions across 2300 expert demonstrations of conversational web navigation. Our benchmark covers abroad range of patterns on over 150 real-world websites and can be used to train and evaluate agents in diverse scenarios. Due to the magnitude of information present, Large Language Models (LLMs) cannot process entire web pages in real-time. To solve this bottleneck, we design a retrieval-inspired model that efficiently prunes HTML pages by ranking relevant elements. We use the selected elements, along with screenshots and action history, to assess a variety of models for their ability to replicate human behavior when navigating the web. Our experiments span from small text-only to proprietary multimodal LLMs. We find that smaller fi

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

R - Projekt Ramcoveho programu EK

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 41st International Conference on Machine Learning

ISBN

979-8-3313-0223-8

ISSN

2640-3498

e-ISSN

—

Number of pages

50

Pages from-to

1-50

Publisher name

Proceedings of Machine Learning Research (PMLR)

Place of publication

San Diego, USA

Event location

Wien, Austria

Event date

Jul 21, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—