lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(cli): add eval_model argument

Browse Source
This commit is contained in:
cui0711
2026-02-05 16:56:39 +08:00
parent 63484c7b7b
commit 1e9281a1ab
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
run.py
View File

@@ -85,7 +85,7 @@ def config() -> argparse.Namespace:
parser.add_argument("--screen_width", type=int, default=1920)
parser.add_argument("--screen_height", type=int, default=1080)
parser.add_argument("--sleep_after_execution", type=float, default=0.0)
parser.add_argument("--max_steps", type=int, default=15)
parser.add_argument("--max_steps", type=int, default=8)
parser.add_argument("--enable_recording", action="store_true", help="Enable video recording (disabled by default)")
# agent config
@@ -100,6 +100,7 @@ def config() -> argparse.Namespace:
parser.add_argument("--top_p", type=float, default=0.9)
parser.add_argument("--max_tokens", type=int, default=16384)
parser.add_argument("--stop_token", type=str, default=None)
parser.add_argument("--eval_model", type=str, default="gpt-5.2-chat-latest")
# example config
parser.add_argument("--domain", type=str, default="all")
@@ -161,6 +162,7 @@ def test(args: argparse.Namespace, test_all_meta: dict) -> None:
os_type = "Windows",
require_a11y_tree=args.observation_type
in ["a11y_tree", "screenshot_a11y_tree", "som"],
eval_model=args.eval_model
)
# get actual VM screen size after environment initialization