Papers › ScreenAgent: A Vision Language Model-driven Computer Control Agent

ScreenAgent: A Vision Language Model-driven Computer Control Agent

9 Feb 2024arXiv:2402.07945archive 2025-07-28

Runliang Niu, Jindong Li, Shiqi Wang, Yali Fu, Xiyu Hu, Xueyuan Leng, He Kong, Yi Chang, Qi Wang

Existing Large Language Models (LLM) can invoke a variety of tools and APIs to complete complex tasks. The computer, as the most powerful and universal tool, could potentially be controlled directly by a trained LLM agent. Powered by the computer, we can hopefully build a more generalized agent to assist humans in various daily digital works. In this paper, we construct an environment for a Vision Language Model (VLM) agent to interact with a real computer screen. Within this environment, the agent can observe screenshots and manipulate the Graphics User Interface (GUI) by outputting mouse and keyboard actions. We also design an automated control pipeline that includes planning, acting, and reflecting phases, guiding the agent to continuously interact with the environment and complete multi-step tasks. Additionally, we construct the ScreenAgent Dataset, which collects screenshots and action sequences when completing a variety of daily computer tasks. Finally, we trained a model, ScreenAgent, which achieved computer control capabilities comparable to GPT-4V and demonstrated more precise UI positioning capabilities. Our attempts could inspire further research on building a generalist LLM agent. The code is available at \url{https://github.com/niuzaisheng/ScreenAgent}.

PaperPDFCodeCode 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="2402.07945")

Code

Syntology Ran 6 of 9 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

niuzaisheng/screenagent officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

9 samples harvested; 6 ran; 0 honoured the contract we drafted; 3 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.

6ran
3unverified

Licence: 9 of the 9 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 niuzaisheng/ScreenAgent. “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.

compute_bleu niuzaisheng/ScreenAgent/client/bleu.py official repository ran no licence file found · pointer only · 49289a7f94c227bd · report
data_collator niuzaisheng/ScreenAgent/train/finetune_ScreenAgent.py official repository ran licence not identified · pointer only · ad5ba95300a1cc7a · report
load_image_from_base64 niuzaisheng/ScreenAgent/train/cogagent_model_worker.py official repository ran licence not identified · pointer only · 6493522dff8f8fa5 · report
pack_ard niuzaisheng/ScreenAgent/client/asyncvnc.py official repository ran licence not identified · pointer only · 625f66bc3b7b4b5b · report
read_int niuzaisheng/ScreenAgent/client/asyncvnc.py official repository ran licence not identified · pointer only · 6741565cee168112 · report
read_text niuzaisheng/ScreenAgent/client/asyncvnc.py official repository ran licence not identified · pointer only · 52dc9a4327ee52bd · report
convert_mouse_button niuzaisheng/ScreenAgent/client/base.py official repository unverified licence not identified · pointer only · c87254327d5ba881 · report
find_non_json_span_from_text niuzaisheng/ScreenAgent/client/action.py official repository unverified licence not identified · pointer only · 3679d1592673c770 · report
split_json_span_and_non_json_span_from_text niuzaisheng/ScreenAgent/client/action.py official repository unverified licence not identified · pointer only · 6bf13d2e007c2458 · report

Tasks

Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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