List your company

Open-Domain Question Answering on Bamboogle

18.4Joint Answer-Evidence ScoreInitial (no search)
0.32485.01749.7114.4026May 21, 2026May 22, 2026May 23, 2026May 24, 2026May 25, 2026May 26, 2026May 28, 2026

Evaluation results

MethodLinks
Initial (no search)search=false2026.0518.4—
EVE-Agentsearch=true2026.056.4—
Dr. Zerosearch=true2026.054—
Initial (search)search=true2026.052.4—
HiPRAGBackbone=Qwen2.5-7B-Instruct2026.052.2347.2
HiPRAGBackbone=Qwen2.5-3B-Instruct2026.052.0836.8
StepSearchBackbone=Qwen2.5-7B-Instruct2026.051.8449.6
StepSearchBackbone=Qwen2.5-3B-Instruct2026.051.727.2
Search-R1Backbone=Qwen2.5-3B-Instruct2026.051.5340.8
RFTBackbone=Qwen2.5-3B-Instruct2026.051.440.8
RFTBackbone=Qwen2.5-7B-Instruct2026.051.3642.4
SAASBackbone=Qwen2.5-3B-Instruct2026.051.2344.8
Search-R1Backbone=Qwen2.5-7B-Instruct2026.051.1540
SAASBackbone=Qwen2.5-7B-Instruct2026.051.0249.6
Direct InferenceBackbone=Qwen2.5-3B-Instruct2026.05—28.8
Direct InferenceBackbone=Qwen2.5-7B-Instruct2026.05—40