CogAgent: A Visual Language Model for GUI Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Wenyi, Wang, Weihan, Lv, Qingsong, Xu, Jiazheng, Yu, Wenmeng, Ji, Junhui, Wang, Yan, Wang, Zihan, Zhang, Yuxuan, Li, Juanzi, Xu, Bin, Dong, Yuxiao, Ding, Ming, Tang, Jie
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917879129047040
author Hong, Wenyi
Wang, Weihan
Lv, Qingsong
Xu, Jiazheng
Yu, Wenmeng
Ji, Junhui
Wang, Yan
Wang, Zihan
Zhang, Yuxuan
Li, Juanzi
Xu, Bin
Dong, Yuxiao
Ding, Ming
Tang, Jie
author_facet Hong, Wenyi
Wang, Weihan
Lv, Qingsong
Xu, Jiazheng
Yu, Wenmeng
Ji, Junhui
Wang, Yan
Wang, Zihan
Zhang, Yuxuan
Li, Juanzi
Xu, Bin
Dong, Yuxiao
Ding, Ming
Tang, Jie
contents People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution of 1120*1120, enabling it to recognize tiny page elements and text. As a generalist visual language model, CogAgent achieves the state of the art on five text-rich and four general VQA benchmarks, including VQAv2, OK-VQA, Text-VQA, ST-VQA, ChartQA, infoVQA, DocVQA, MM-Vet, and POPE. CogAgent, using only screenshots as input, outperforms LLM-based methods that consume extracted HTML text on both PC and Android GUI navigation tasks -- Mind2Web and AITW, advancing the state of the art. The model and codes are available at https://github.com/THUDM/CogVLM, with a new version of CogAgent-9B-20241220 available at https://github.com/THUDM/CogAgent.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08914
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CogAgent: A Visual Language Model for GUI Agents
Hong, Wenyi
Wang, Weihan
Lv, Qingsong
Xu, Jiazheng
Yu, Wenmeng
Ji, Junhui
Wang, Yan
Wang, Zihan
Zhang, Yuxuan
Li, Juanzi
Xu, Bin
Dong, Yuxiao
Ding, Ming
Tang, Jie
Computer Vision and Pattern Recognition
People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution of 1120*1120, enabling it to recognize tiny page elements and text. As a generalist visual language model, CogAgent achieves the state of the art on five text-rich and four general VQA benchmarks, including VQAv2, OK-VQA, Text-VQA, ST-VQA, ChartQA, infoVQA, DocVQA, MM-Vet, and POPE. CogAgent, using only screenshots as input, outperforms LLM-based methods that consume extracted HTML text on both PC and Android GUI navigation tasks -- Mind2Web and AITW, advancing the state of the art. The model and codes are available at https://github.com/THUDM/CogVLM, with a new version of CogAgent-9B-20241220 available at https://github.com/THUDM/CogAgent.
title CogAgent: A Visual Language Model for GUI Agents
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.08914