List your company

Retrieval-Augmented Question Answering on DeepSearch 2wiki

68Success Rate (SR)Training-Free GRPO
22.2434.124657.88Apr 13, 2026

Evaluation results

MethodLinks
Training-Free GRPOTaskExecutor=Gemini-3.0-flash2026.046839.1
ActiveContextTaskExecutor=Gemini-3.0-flash2026.04687.5
Full ContextTaskExecutor=Gemini-3.0-flash2026.046238.9
SynapseTaskExecutor=Gemini-3.0-flash2026.044283
Mem0TaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.044246.7
Gemini-3.0-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04429.5
Full ContextTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.044033.8
Training-Free GRPOTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.044036.1
AWMTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.043934.2
SynapseTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.043845
ContextCuratorTaskExecutor=gpt-4o-mini, Category=RL-Trained Curator2026.04387.4
ActiveContextTaskExecutor=Gemini-2.5-flash2026.0436.49.6
Gemini-2.5-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04349.1
SynapseTaskExecutor=Gemini-2.5-flash2026.043292.4
gpt-4oTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.043211.2
gpt-4o-miniTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.043010
Qwen2.5-7B-InstructTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.0428.610.5
Full ContextTaskExecutor=Gemini-2.5-flash2026.042840.8
Full ContextTaskExecutor=gpt-4o2026.042838.2
SynapseTaskExecutor=gpt-4o2026.042845.9
Training-Free GRPOTaskExecutor=gpt-4o2026.042838.9
ActiveContextTaskExecutor=gpt-4o2026.04269.3
Training-Free GRPOTaskExecutor=Gemini-2.5-flash2026.042478.3