Papers › CogAgent: A Visual Language Model for GUI Agents

CogAgent: A Visual Language Model for GUI Agents

14 Dec 2023CVPR 2024 1arXiv:2312.08914archive 2025-07-28

Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxuan Zhang, Juanzi Li, Bin Xu, Yuxiao Dong, Ming Ding, Jie Tang

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2312.08914")

Code

Syntology Ran 12 of 18 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 12 ran with no contract checked.

By repository: official repository: 18 samples from 2 repositories, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

THUDM/CogAgent officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
thudm/cogvlm officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
digirl-agent/digirl mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested; 12 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

12ran
6unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

data_collator thudm/cogvlm/finetune_demo/evaluate_cogvlm_demo.py official repository ran Apache-2.0 (permissive) · 54a2b4c8804d95b2 · report
data_collator thudm/cogvlm/finetune_demo/evaluate_cogagent_demo.py official repository ran Apache-2.0 (permissive) · afd5a3b7c43f083d · report
encode_image THUDM/CogAgent/app/client.py official repository ran Apache-2.0 (permissive) · 1f0bc3f4321973e5 · report
override_dist_dtype_device_args thudm/cogvlm/utils/models/cogvlm_model.py official repository ran Apache-2.0 (permissive) · f3df71c28fae6837 · report
postprocess_image thudm/cogvlm/composite_demo/conversation.py official repository ran Apache-2.0 (permissive) · d8de666d9830ab8d · report
postprocess_text thudm/cogvlm/composite_demo/conversation.py official repository ran fingerprinted Apache-2.0 (permissive) · 2ce3e067b29fa052 · report
preprocess_messages THUDM/CogAgent/inference/web_demo.py official repository ran Apache-2.0 (permissive) · 363f5a1eb1b85d3b · report
process_history_and_images THUDM/CogAgent/app/openai_demo.py official repository ran Apache-2.0 (permissive) · 98595f749058567a · report
process_history_and_images THUDM/CogAgent/app/vllm_openai_server.py official repository ran Apache-2.0 (permissive) · e83d1a79f13a1746 · report
process_image_without_resize thudm/cogvlm/basic_demo/web_demo.py official repository ran Apache-2.0 (permissive) · dc039cc4ef751f3a · report
undo_last_round THUDM/CogAgent/inference/web_demo.py official repository ran Apache-2.0 (permissive) · c43bbdf5c24a61ab · report
user THUDM/CogAgent/inference/web_demo.py official repository ran Apache-2.0 (permissive) · 67160abc4bee8174 · report
create_chat_completion THUDM/CogAgent/app/client.py official repository unverified Apache-2.0 (permissive) · 21b986b1859a8a51 · report
formatting_input THUDM/CogAgent/app/client.py official repository unverified Apache-2.0 (permissive) · 7728f4b3ad854aea · report
generate_cogagent THUDM/CogAgent/app/openai_demo.py official repository unverified Apache-2.0 (permissive) · 34b717a187133b8a · report
load_tokenizer_and_model THUDM/CogAgent/finetune/finetune.py official repository unverified Apache-2.0 (permissive) · 459bb9214094ea8f · report
process_batch THUDM/CogAgent/finetune/finetune.py official repository unverified Apache-2.0 (permissive) · 0713ce4249b75fac · report
process_batch_eval THUDM/CogAgent/finetune/finetune.py official repository unverified Apache-2.0 (permissive) · 0c9a09bd7e2934b7 · report

Tasks

Language ModelingLanguage ModellingNatural Language Visual GroundingVisual Question AnsweringVisual Question Answering (VQA)model

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
-3.5 #4 of 6 Archive leaderboard report
Natural Language Visual Grounding ScreenSpot CogAgent Accuracy (%) 47.4 #13 of 18 Archive leaderboard report
Visual Question Answering MM-Vet CogAgent GPT-4 score 52.8 #52 of 231 Archive leaderboard report
Visual Question Answering MM-Vet CogAgent Params 18B #52 of 231 Archive leaderboard report
Visual Question Answering MM-Vet v2 CogAgent-Chat GPT-4 score 34.7±0.2 #20 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections