Spaces:

emrekuruu
/

spreadsheetbench-openenv

Sleeping

44.8 kB

Ctrl+K

1 contributor

SpreadsheetBench: SkillOpt mode=multi — 30-turn code repair with execution feedback, 600 s task budget, training-only gold cell feedback

f24ba1b verified about 1 month ago

test_catalog.py

3.67 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago
test_core.py

11.1 kB
SpreadsheetBench: SkillOpt mode=multi — 30-turn code repair with execution feedback, 600 s task budget, training-only gold cell feedback about 1 month ago
test_executor.py

5.93 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago
test_grader.py

2.78 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago
test_models.py

2.15 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago
test_openenv_app.py

6.48 kB
SpreadsheetBench: SkillOpt mode=multi — 30-turn code repair with execution feedback, 600 s task budget, training-only gold cell feedback about 1 month ago
test_openenv_client.py

2.9 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago
test_openenv_environment.py

5.07 kB
SpreadsheetBench: SkillOpt mode=multi — 30-turn code repair with execution feedback, 600 s task budget, training-only gold cell feedback about 1 month ago
test_package_boundary.py

2.95 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago
test_runtime_assets.py

1.76 kB
Argument descriptions carry format only; environment description is the single home of world rules about 1 month ago