List your company

Open-domain QA on Overall QA Suite (NQ, TriviaQA, PopQA, HotpotQA, 2WikiMultiHopQA, MuSiQue, Bamboogle)

62.3Average EMSDGA-Phase
13.31626.03338.7551.467May 12, 2026

Evaluation results

MethodLinks
SDGA-PhaseFramework=ZeroSearch, Model=Qwen2.5-7B, Search Depth (Smax)=52026.0562.3
SDGA-AutoFramework=ZeroSearch, Model=Qwen2.5-7B, Search Depth (Smax)=52026.0558.3
SDGA-PhaseFramework=ZeroSearch, Model=Qwen2.5-3B, Search Depth (Smax)=52026.0556.3
SDGA-AutoFramework=ZeroSearch, Model=Qwen2.5-3B, Search Depth (Smax)=52026.0552.9
GRPO-FullFramework=ZeroSearch, Model=Qwen2.5-7B2026.0550.9
SDGA-PhaseFramework=Search-R1, Model=Qwen2.5-7B, Search Depth (Smax)=52026.0547.1
GRPO-HalfFramework=ZeroSearch, Model=Qwen2.5-7B2026.0544.7
GRPO-FullFramework=ZeroSearch, Model=Qwen2.5-3B2026.0544.5
SDGA-AutoFramework=Search-R1, Model=Qwen2.5-7B, Search Depth (Smax)=52026.0542.2
SDGA-PhaseFramework=Search-R1, Model=Qwen2.5-3B, Search Depth (Smax)=52026.0540.9
SDGA-AutoFramework=Search-R1, Model=LLaMA-3.2-3B-Base, Search Depth (Smax)=52026.0539.6
SDGA-PhaseFramework=Search-R1, Model=LLaMA-3.2-3B-Base, Search Depth (Smax)=52026.0539.4
GRPO-HalfFramework=ZeroSearch, Model=Qwen2.5-3B2026.0539.3
GRPO-FullFramework=Search-R1, Model=Qwen2.5-7B2026.0539
SDGA-PhaseFramework=ZeroSearch, Model=LLaMA-3.2-3B-Base, Search Depth (Smax)=52026.0538.8
SDGA-AutoFramework=ZeroSearch, Model=LLaMA-3.2-3B-Base, Search Depth (Smax)=52026.0538.5
SDGA-AutoFramework=Search-R1, Model=Qwen2.5-3B, Search Depth (Smax)=52026.0537.5
GRPO-FullFramework=Search-R1, Model=Qwen2.5-3B2026.0535.9
GRPO-HalfFramework=Search-R1, Model=Qwen2.5-7B2026.0534.4
GRPO-FullFramework=ZeroSearch, Model=LLaMA-3.2-3B-Base2026.0533.6
GRPO-HalfFramework=Search-R1, Model=Qwen2.5-3B2026.0533.2
GRPO-FullFramework=Search-R1, Model=LLaMA-3.2-3B-Base2026.0531.9
GRPO-HalfFramework=ZeroSearch, Model=LLaMA-3.2-3B-Base2026.0529.7
GRPO-HalfFramework=Search-R1, Model=LLaMA-3.2-3B-Base2026.0528.6
SDGA-AntiFramework=ZeroSearch, Model=Qwen2.5-7B, Search Depth (Smax)=52026.0522.4
SDGA-AntiFramework=Search-R1, Model=Qwen2.5-7B, Search Depth (Smax)=52026.0520.5
SDGA-AntiFramework=ZeroSearch, Model=Qwen2.5-3B, Search Depth (Smax)=52026.0520.4
SDGA-AntiFramework=Search-R1, Model=Qwen2.5-3B, Search Depth (Smax)=52026.0518.3
SDGA-AntiFramework=ZeroSearch, Model=LLaMA-3.2-3B-Base, Search Depth (Smax)=52026.0516.2
SDGA-AntiFramework=Search-R1, Model=LLaMA-3.2-3B-Base, Search Depth (Smax)=52026.0515.2