@inproceedings{iong-etal-2024-openwebagent,
title = "{O}pen{W}eb{A}gent: An Open Toolkit to Enable Web Agents on Large Language Models",
author = "Iong, Iat Long and
Liu, Xiao and
Chen, Yuxuan and
Lai, Hanyu and
Yao, Shuntian and
Shen, Pengbo and
Yu, Hao and
Dong, Yuxiao and
Tang, Jie",
editor = "Cao, Yixin and
Feng, Yang and
Xiong, Deyi",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-demos.8",
doi = "10.18653/v1/2024.acl-demos.8",
pages = "72--81",
abstract = "We introduce OpenWebAgent, an open toolkit designed to optimize web automation by integrating both large language models (LLMs) and large multimodal models (LMMs). This toolkit focuses on enhancing human-computer interactions on the web, simplifying complex tasks through an advanced HTML parser, a rapid action generation module, and an intuitive user interface. At the core of OpenWebAgent is an innovative web agent framework that uses a modular design to allow developers to seamlessly integrate a variety of models and tools to process web information and automate tasks on the web. This enables the development of powerful, task-oriented web agents, significantly enhancing user experience and operational efficiency on the web. The OpenWebAgent framework, Chrome plugin, and demo video are available at https://github.com/THUDM/OpenWebAgent/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iong-etal-2024-openwebagent">
<titleInfo>
<title>OpenWebAgent: An Open Toolkit to Enable Web Agents on Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iat</namePart>
<namePart type="given">Long</namePart>
<namePart type="family">Iong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanyu</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuntian</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengbo</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiao</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce OpenWebAgent, an open toolkit designed to optimize web automation by integrating both large language models (LLMs) and large multimodal models (LMMs). This toolkit focuses on enhancing human-computer interactions on the web, simplifying complex tasks through an advanced HTML parser, a rapid action generation module, and an intuitive user interface. At the core of OpenWebAgent is an innovative web agent framework that uses a modular design to allow developers to seamlessly integrate a variety of models and tools to process web information and automate tasks on the web. This enables the development of powerful, task-oriented web agents, significantly enhancing user experience and operational efficiency on the web. The OpenWebAgent framework, Chrome plugin, and demo video are available at https://github.com/THUDM/OpenWebAgent/.</abstract>
<identifier type="citekey">iong-etal-2024-openwebagent</identifier>
<identifier type="doi">10.18653/v1/2024.acl-demos.8</identifier>
<location>
<url>https://aclanthology.org/2024.acl-demos.8</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>72</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenWebAgent: An Open Toolkit to Enable Web Agents on Large Language Models
%A Iong, Iat Long
%A Liu, Xiao
%A Chen, Yuxuan
%A Lai, Hanyu
%A Yao, Shuntian
%A Shen, Pengbo
%A Yu, Hao
%A Dong, Yuxiao
%A Tang, Jie
%Y Cao, Yixin
%Y Feng, Yang
%Y Xiong, Deyi
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F iong-etal-2024-openwebagent
%X We introduce OpenWebAgent, an open toolkit designed to optimize web automation by integrating both large language models (LLMs) and large multimodal models (LMMs). This toolkit focuses on enhancing human-computer interactions on the web, simplifying complex tasks through an advanced HTML parser, a rapid action generation module, and an intuitive user interface. At the core of OpenWebAgent is an innovative web agent framework that uses a modular design to allow developers to seamlessly integrate a variety of models and tools to process web information and automate tasks on the web. This enables the development of powerful, task-oriented web agents, significantly enhancing user experience and operational efficiency on the web. The OpenWebAgent framework, Chrome plugin, and demo video are available at https://github.com/THUDM/OpenWebAgent/.
%R 10.18653/v1/2024.acl-demos.8
%U https://aclanthology.org/2024.acl-demos.8
%U https://doi.org/10.18653/v1/2024.acl-demos.8
%P 72-81
Markdown (Informal)
[OpenWebAgent: An Open Toolkit to Enable Web Agents on Large Language Models](https://aclanthology.org/2024.acl-demos.8) (Iong et al., ACL 2024)
ACL
- Iat Long Iong, Xiao Liu, Yuxuan Chen, Hanyu Lai, Shuntian Yao, Pengbo Shen, Hao Yu, Yuxiao Dong, and Jie Tang. 2024. OpenWebAgent: An Open Toolkit to Enable Web Agents on Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 72–81, Bangkok, Thailand. Association for Computational Linguistics.