List your company

Ambiguous Question Answering on Museum Artifact Dataset Amb. 1.0 (test)

65Answer AccuracyQwen3-VL-8B (Direct)
47.3251.9156.561.09Jul 7, 2026

Evaluation results

MethodLinks
Qwen3-VL-8B (Direct)search=disabled, reliability control=none2026.076533673.33
VaseAgent (w/o GRPO)search=enabled, reliability control=source/response control, GRPO selection=disabled2026.075546542.84
VaseAgent (Full)search=enabled, reliability control=complete system, GRPO selection=enabled2026.075544563.02
Qwen3-VL-8B + Searchsearch=enabled, reliability control=none2026.074853462.64