Papers › GUICourse: From General Vision Language Models to Versatile GUI Agents

GUICourse: From General Vision Language Models to Versatile GUI Agents

17 Jun 2024arXiv:2406.11317archive 2025-07-28

Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan YAO, Yankai Lin, Zhiyuan Liu, Maosong Sun

Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to help humans finish GUI navigation tasks. However, current VLMs are challenged in terms of fundamental abilities (OCR and grounding) and GUI knowledge (the functions and control methods of GUI elements), preventing them from becoming practical GUI agents. To solve these challenges, we contribute GUICourse, a suite of datasets to train visual-based GUI agents from general VLMs. First, we introduce the GUIEnv dataset to strengthen the OCR and grounding capabilities of VLMs. Then, we introduce the GUIAct and GUIChat datasets to enrich their knowledge of GUI components and interactions. Experiments demonstrate that our GUI agents have better performance on common GUI tasks than their baseline VLMs. Even the small-size GUI agent (with 3.1B parameters) can still work well on single-step and multi-step GUI tasks. Finally, we analyze the different varieties in the training stage of this agent by ablation study. Our source codes and datasets are released at https://github.com/yiye3/GUICourse.

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="2406.11317")

Code

Syntology Ran 15 of 16 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 14 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yiye3/guicourse officialmentioned in papermentioned on GitHub 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

16 samples harvested; 15 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
14ran
1unverified

Licence: 16 of the 16 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 yiye3/guicourse. “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.

convert_guiact_to_qwen_format yiye3/guicourse/data_preprocess/merge_data.py official repository ran no licence file found · pointer only · 30255d9ba1ef6094 · report
convert_guienv_to_qwen_format yiye3/guicourse/data_preprocess/merge_data.py official repository ran no licence file found · pointer only · a8cc5e1c280fda6a · report
decode_base64_to_image yiye3/guicourse/data_load.py official repository ran no licence file found · pointer only · ecc04078e2043893 · report
eval_bbox2text yiye3/guicourse/evaluation/eval_single_action.py official repository ran no licence file found · pointer only · 335b6330b9af2164 · report
infer yiye3/guicourse/Qwen-SFT&Infer/infer.py official repository ran no licence file found · pointer only · f068f39a25e1a842 · report
iou yiye3/guicourse/utils.py official repository ran no licence file found · pointer only · 036a213486b2f4b4 · report
is_pass_check yiye3/guicourse/data_preprocess/convert_to_sft_instructions.py official repository ran no licence file found · pointer only · d2d934fd1a05b9e1 · report
load_data yiye3/guicourse/Qwen-SFT&Infer/infer.py official repository ran no licence file found · pointer only · 6ec4ec7ae41b4345 · report
load_model_and_tokenizer yiye3/guicourse/Qwen-SFT&Infer/infer.py official repository ran no licence file found · pointer only · baaebe9658032c54 · report
parse_box yiye3/guicourse/utils.py official repository ran no licence file found · pointer only · 4b39866ea5e2b70d · report
parse_point yiye3/guicourse/utils.py official repository ran no licence file found · pointer only · cb7585c0b75f73f9 · report
preprocess yiye3/guicourse/Qwen-SFT&Infer/finetune.py official repository ran · our draft was wrong no licence file found · pointer only · 8b733c9fc590e4c1 · report
read_data yiye3/guicourse/data_preprocess/convert_parquet_to_png.py official repository ran no licence file found · pointer only · aedd559eaebb8985 · report
read_json yiye3/guicourse/data_load.py official repository ran no licence file found · pointer only · 61ec4f7400ef2dac · report
read_parquet yiye3/guicourse/data_load.py official repository ran no licence file found · pointer only · 4906b1a9823dc7d6 · report
elements_visual yiye3/guicourse/data_visualization.py official repository unverified no licence file found · pointer only · 25de1b1cb65b6b3c · report

Tasks

Natural Language Visual GroundingOptical Character Recognition (OCR)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Visual Grounding ScreenSpot Qwen-GUI Accuracy (%) 28.6 #15 of 18 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