Commit Graph

16 Commits

Author SHA1 Message Date
yuanmengqi
523d553e88 feat: add client password argument to multiple agents and scripts
- Introduced `--client_password` argument in `run_multienv_aguvis.py`, `run_multienv_claude.py`, and `run_multienv_gta1.py` for enhanced security and flexibility.
- Updated agent classes (`PromptAgent`, `AguvisAgent`, `GTA1Agent`) to accept and utilize `client_password` for improved configuration.
- Modified evaluation guidelines to reflect the new client password requirement.
- Ensured existing logic remains intact while enhancing functionality for better user experience.
2025-07-27 16:11:23 +00:00
Yan98
0a5058342d init (#246) 2025-07-10 00:29:42 +08:00
MillanK
51f5ddea04 Add Jedi agent implementation to mm_agents (#192)
* feat: implement Jedi agent

* chore: code clean
2025-05-10 19:55:33 +08:00
Thomas Kuntz
5678b510d7 fix: Invalid escape sequence in prompts (#191)
Fixes the warning: SyntaxWarning: invalid escape sequence '\`'
2025-05-10 18:19:07 +08:00
Shihao Liang
b92c716df7 Dev/uitars 15 (#181)
* debug uitars1.0, add uitars1.5

* update pyautogui parser

* modify function name

* update parser

* update prompt
2025-04-21 13:44:08 +08:00
Shihao Liang
0bc1e08440 Dev/uitars (#129)
* init uitars

* change agent class name
2025-02-08 12:49:40 +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
Timothyxxx
d79d5d2c01 Clean Code 2024-03-27 14:46:29 +08:00
Timothyxxx
ace5842505 Fix typo 2024-03-19 18:57:47 +08:00
David Chang
4df088e2ad ver Mar19thv2
supplemented at info back for som setting
2024-03-19 18:41:55 +08:00
Timothyxxx
1ad4527e8b Change SoM input and output 2024-03-15 22:10:35 +08:00
Timothyxxx
030574e316 Improve on mmagents prompts; initialize online tasks from Mind2Web 2024-02-22 22:01:22 +08:00
Timothyxxx
32bcdd0937 Modify the logic of SoM agent 2024-02-01 18:58:22 +08:00
Timothyxxx
6952b45de4 Improve on agent and tasks configs 2024-01-26 23:30:04 +08:00
Timothyxxx
f88331416c Refactor baselines code implementations 2024-01-20 18:55:21 +08:00
Timothyxxx
09f3e776ae Initialize all baselines: screenshot, a11y tree, both, SoM, SeeAct 2024-01-20 00:13:46 +08:00