List your company

Retrieval-Augmented Question Answering on DeepSearch TriviaQA

78Success Rate (SR)ActiveContext
33.2844.8956.568.11Apr 13, 2026

Evaluation results

MethodLinks
ActiveContextTaskExecutor=Gemini-3.0-flash2026.04783.2
Full ContextTaskExecutor=Gemini-3.0-flash2026.047620.4
Training-Free GRPOTaskExecutor=Gemini-3.0-flash2026.047616.7
SynapseTaskExecutor=Gemini-3.0-flash2026.046851.2
ActiveContextTaskExecutor=Gemini-2.5-flash2026.04663.7
ActiveContextTaskExecutor=gpt-4o2026.04663.6
Gemini-3.0-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04664.4
Training-Free GRPOTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.046418.3
Gemini-2.5-flashTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04644.6
Mem0TaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.046227.6
ContextCuratorTaskExecutor=gpt-4o-mini, Category=RL-Trained Curator2026.04625
Training-Free GRPOTaskExecutor=Gemini-2.5-flash2026.046038.4
Full ContextTaskExecutor=Gemini-2.5-flash2026.045820.6
Full ContextTaskExecutor=gpt-4o2026.045820.7
Training-Free GRPOTaskExecutor=gpt-4o2026.045819.6
gpt-4oTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04586.9
AWMTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.045616.4
gpt-4o-miniTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04567.3
Qwen2.5-7B-InstructTaskExecutor=gpt-4o-mini, Category=Zero-Shot Curators2026.04526.5
Full ContextTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.045019.7
SynapseTaskExecutor=gpt-4o-mini, Category=Baselines & Retrieval-Based Memory2026.043742.7
SynapseTaskExecutor=gpt-4o2026.043642
SynapseTaskExecutor=Gemini-2.5-flash2026.043586.1