lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,374 Commits 3 Branches 0 Tags
os_world
Commit Graph

36 Commits

Author SHA1 Message Date
cui0711
716d82f4d1 feat: add flexible recording control and improve execution logging 2026-01-30 16:28:13 +08:00
Bowen Yang
662826f57e fix(os_symphony):prompt (#402) 
* add_os_symphony

* fix(os_symphony)

* fix(os_symphony):prompt

---------

Co-authored-by: Tianbao Xie <47296835+Timothyxxx@users.noreply.github.com>
 2025-12-29 20:45:36 +08:00
xuetf
410ec63a89 Add EvoCUA Support (#401) 
* evocua init

* setup max_token

---------

Co-authored-by: xuetaofeng <xuetaofeng@meituan.com>
Co-authored-by: Tianbao Xie <47296835+Timothyxxx@users.noreply.github.com>
 2025-12-23 20:46:23 +08:00
Bowen Yang
031696e83c fix os_symphony (#400) 
* add_os_symphony

* fix(os_symphony)

---------

Co-authored-by: Tianbao Xie <47296835+Timothyxxx@users.noreply.github.com>
 2025-12-23 20:45:30 +08:00
Qichen Fu
903ed36715 Add Claude Sonnet 4.5 support and improve action handling (#362) 
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude <noreply@anthropic.com>
 2025-11-14 13:54:32 +08:00
Subash Shibu
3167339e45 Add hosted GBOX agent for OSWorld evaluation (#376) 2025-11-13 13:13:31 +08:00
Atharva Gundawar
9f97535ef9 oswrold agent wrapper for trained v7 (#360) 2025-10-18 02:29:15 +08:00
Xinyuan Wang
f9e9273b3b OpenCUA-72B (#354) 
* use aws pub ip

* os task fix: set the default dim screen time to be 300s

* OpenCUA-72B

* update password

* update

* update

* update opencua72b agent

* change provider ip

---------

Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
 2025-10-13 10:39:33 +08:00
Yanxiao Zhao
a4f8fe2f00 Add autoglm-os-9b-v (#344) 
* update for autoglm-v

* Update run_autoglm.py

---------

Co-authored-by: hanyullai <hanyullai@outlook.com>
 2025-09-24 19:43:28 +08:00
alexandruilie7
f59cf00cae Add ui agent (#343) 
* add uipath agent

* readme update
 2025-09-24 19:42:46 +08:00
molanhand
7213eca069 support mano agent (#338) 
Co-authored-by: Fei Hu <molanhand@users.noreply.github.com>
 2025-09-16 18:10:29 +08:00
Adam Yanxiao Zhao
aa05f6cc26 Add AutoGLM-OS agent (#309) 
* autoglm-os initialize

* clean code

* chore: use proxy for download setup

* feat(autoglm-os): add parameter to toggle images

* fix: use temporary directory for files pulled from the vm to prevent potential collision when running multiple instances of the same task in parallel

* update

* add client_password

* update multienv

* fix

* fix prompt

* fix prompt

* fix prompt

* fix sys prompt

* feat: use proxy in file evaluator

* fix client_password

* fix note_prompt

* fix autoglm agent cmd type

* fix

* revert: fix: use temporary directory for files pulled from the vm to prevent potential collision when running multiple instances of the same task in parallel

reverts commit bab5473eea1de0e61b0e1d68b23ce324a5b0ee57

* feat(autoglm): setup tools

* fix(autoglm): remove second time of get a11y tree

* add osworld server restart

* Revert "add osworld server restart"

This reverts commit 7bd9d84122e246ce2a26de0e49c25494244c2b3d.

* fix _launch_setup

* fix autoglm agent tools & xml tree

* fix desktop_env

* fix bug for tool name capitalization

* fix: always use proxy for setup download

* add fail after exceeding max turns

* fix(autoglm): avoid adding image to message when screenshot is empty

* fix maximize_window

* fix maximize_window

* fix maximize_window

* fix import browsertools module bug

* fix task proxy config bug

* restore setup

* refactor desktop env

* restore image in provider

* restore file.py

* refactor desktop_env

* quick fix

* refactor desktop_env.step

* fix our env reset

* add max truns constraint

* clean run script

* clean lib_run_single.py

---------

Co-authored-by: hanyullai <hanyullai@outlook.com>
Co-authored-by: JingBh <jingbohao@yeah.net>
 2025-08-17 12:08:40 +08:00
Xinyuan Wang
3d32556085 Uitars/dev (#291) 
* use aws pub ip

* os task fix: set the default dim screen time to be 300s

* add all the uitars agents:
1. run_multienv_uitars.py: Qwen2VL-based UITARS models
2. run_multienv_uitars15_v1.py: UITARS1.5-7B
3. run_multienv_uitars15_v2.py: SeedVL1.5 thining/non-thinking

---------

Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
 2025-07-31 08:52:27 +08:00
yuanmengqi
39e5baf5ae fix: remove unnecessary sleep and observation retrieval in run_single_example function 2025-07-25 15:51:20 +00:00
Yuan Mengqi
0a37cccd53 update claude (#280) 
* add uitars agent code

* improve claude

* improve claude

* improve claude

* improve claude

* improve claude
 2025-07-23 03:35:49 +08:00
yuanmengqi
91bc6bb6ce Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-07-20 07:55:57 +00:00
yuanmengqi
88d5639a2a Compatible with agents that cannot use runtime log 2025-07-20 07:55:53 +00:00
Xinyuan Wang
e10dd9267c Wxy/opencua (#274) 
* OpenCUA Agent code base

* update url

* debug, modify url input

* debug opencua

* show result

* debug agent history overlap

* modify opencua agent; add comment lines

* update parallel; clean code; use sleep 3s

* ui-tars-0717
 2025-07-20 15:52:23 +08:00
Xinyuan Wang
0f2655249c Wxy/opencua (#260) 
* OpenCUA Agent code base

* update url

* debug, modify url input

* debug opencua

* show result

* debug agent history overlap

* modify opencua agent; add comment lines
 2025-07-16 17:53:12 +08:00
Xinyuan Wang
db83b9cb2c Wxy/opencua (#256) 
* OpenCUA Agent code base

* update url

* debug, modify url input
 2025-07-14 20:26:39 +08:00
yuanmengqi
aee1207fff fix error 2025-06-09 04:20:59 +00:00
adlsdztony
ae473d8673 fix: remove pending checks from actions to prevent json serialization issues 2025-06-04 14:20:02 +00:00
yuanmengqi
228849ab03 add openai cua agent 2025-05-31 11:22:38 +00:00
Xinyuan Wang
d626cc90d9 Modify: wait for initial env to be ready (#139) 2025-02-25 21:08:25 +08:00
Junli Wang
1503eb3994 Finish Aguvis eval on OSWorld (#107) 
* Initialize Aguvis eval on OSWorld

* Debug

* Debug

* v1, internal version

* Add experiments script

* Fix minor bugs

* Update new endpoint

* Update ip

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Fix model name

* Fix docker close issues; update prompting

* Fix missed

* Fix the default port to avoid crashing on examples like '_update_browse_history_setup'

* Fix server and chromium ports in setup

* Revert and add missed dependency

* Add VLC port for docker

* Update

* Aguvis Grounding

* Add Aguvis as planner

* fix parse bug

* fix pause

* fix planner prompt

* Aguvis Grounding

* fix

* fix

* fix

* add logger for each example

* Modify Aguvis Planner Prompts

* fix logger setup

* fix absolute coordinates

* Finish Aguvis Evaluation on OSWorld

* Merge origin/main into junli/aguvis

* Remove screenshot

---------

Co-authored-by: Tianbao Xie <tianbaoxie@U-492FC39R-0217.local>
Co-authored-by: Timothyxxx <384084775@qq.com>
Co-authored-by: FredWuCZ <fredwucz@outlook.com>
 2024-11-24 16:43:25 +08:00
tsuky_chen
1fd8b66fde debug/timeout (#59) 2024-07-24 08:31:42 +08:00
Timothyxxx
9c75df5dce Clean code; Refactor environment to pass screenshot content instead of path 2024-04-13 23:34:01 +08:00
Timothyxxx
8e760fd450 Disable wandb temporarily, speedup the environment step speed by remove useless a11y tree re-get and terminal output 2024-03-19 08:57:05 +08:00
Timothyxxx
f992d1f694 Disable a11y tree temporarily 2024-03-18 21:43:35 +08:00
Timothyxxx
c1c7ac298f Update claude endpoint 2024-03-18 14:59:02 +08:00
Jason Lee
576248ae18 uncomment timer 2024-03-18 12:02:34 +08:00
Jason Lee
8080828a84 update wandb settings 2024-03-18 00:02:41 +08:00
Jason Lee
48aedb09a7 add wandb settings, remember to set WANDB_KEY 2024-03-17 22:30:29 +08:00
Timothyxxx
639f8c7db8 Fix small bugs in max time limit setting 2024-03-16 14:34:40 +08:00
Jason Lee
053da203b8 new timer, but need to set in setting.json file, need to be upgraded into parameters 2024-03-16 12:36:23 +08:00
Jason Lee
44679724b8 try new timer 2024-03-16 11:54:45 +08:00