List your company

Visual Question Answering on Museum Artifact Dataset V-Only 1.0 (test)

44Accuracy (A)Qwen3-VL-8B (Direct)
19.0425.523238.48Jul 7, 2026

Evaluation results

MethodLinks
Qwen3-VL-8B (Direct)search=disabled, reliability control=none2026.074454452.83
VaseAgent (Full)search=enabled, reliability control=complete system, GRPO selection=enabled2026.072466342.47
Qwen3-VL-8B + Searchsearch=enabled, reliability control=none2026.072079201.86
VaseAgent (w/o GRPO)search=enabled, reliability control=source/response control, GRPO selection=disabled2026.072076242.18