Spaces:

dnanh
/

vilexagent

Paused

App Files Files Community

vilexagent / evaluation /run_evaluation.py

Commit History

phase 4: Complete agent UI and final evaluation run

1b14988

Nhat Anh commited on May 7

Phase 3: full 30-question evaluation complete - ViLexAgent groundedness 4.35 vs 2.20 baseline

5a0fbb7

Nhat Anh commited on May 6