List your company

Retrieval-Augmented Question Answering on DeepSearch HotpotQA

56Success RateActiveContext
16.4826.743747.26Apr 13, 2026

Evaluation results

MethodLinks
ActiveContextTaskExecutor=Gemini-3.0-flash2026.04567.4
Full ContextTaskExecutor=Gemini-3.0-flash2026.045253.5
Training-Free GRPOTaskExecutor=Gemini-3.0-flash2026.044660.5
ActiveContextTaskExecutor=gpt-4o2026.04387.4
Gemini-3.0-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04388.7
Training-Free GRPOTaskExecutor=gpt-4o2026.043435.5
ContextCuratorTaskExecutor=gpt-4o-mini, Category=RL-Trained Curator2026.04347.3
SynapseTaskExecutor=Gemini-3.0-flash2026.0432149.2
Full ContextTaskExecutor=Gemini-2.5-flash2026.043235.5
Full ContextTaskExecutor=gpt-4o2026.043235.5
Gemini-2.5-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04328.3
ActiveContextTaskExecutor=Gemini-2.5-flash2026.0431.88.4
Mem0TaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.043152.1
Full ContextTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.043037.2
Training-Free GRPOTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.043039.1
gpt-4oTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.043011.4
Training-Free GRPOTaskExecutor=Gemini-2.5-flash2026.042876.5
gpt-4o-miniTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.042810.9
Qwen2.5-7B-InstructTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.042810
SynapseTaskExecutor=Gemini-2.5-flash2026.0426135.3
AWMTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.042536.2
SynapseTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.042055.9
SynapseTaskExecutor=gpt-4o2026.041852.1