Question Answering on PopQA (pass@1)
58.4pass@1Search-R1-7B + SSP
Evaluation results
| Method | Links | |
|---|---|---|
| Search-R1-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 58.4 | |
| Search-R1-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 57.2 | |
| R-Search-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 56.8 | |
| Qwen2.5-7B-Base + SSPTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=true2025.10 | 56 | |
| LLaMA-3.1-8B + SSPTraining Paradigm=Generalization Across Model Families, SSP Integration=true2025.10 | 55.4 | |
| Qwen3-8B + SSPTraining Paradigm=Generalization Across Model Families, SSP Integration=true2025.10 | 55 | |
| Qwen2.5-32B-Instruct + SSPTraining Paradigm=Scaling to Larger Models, SSP Integration=true2025.10 | 55 | |
| Qwen2.5-14B-Instruct + SSPTraining Paradigm=Scaling to Larger Models, SSP Integration=true2025.10 | 54.6 | |
| R-Search-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 53.8 | |
| Qwen2.5-14B-InstructTraining Paradigm=Scaling to Larger Models, SSP Integration=false2025.10 | 53.8 | |
| Qwen2.5-32B-InstructTraining Paradigm=Scaling to Larger Models, SSP Integration=false2025.10 | 53.4 | |
| ZeroSearch-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 53 | |
| Qwen2.5-7B-Instruct + SSPTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=true2025.10 | 51.8 | |
| Qwen3-8BTraining Paradigm=Generalization Across Model Families, SSP Integration=false2025.10 | 50.8 | |
| ZeroSearch-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 50.2 | |
| LLaMA-3.1-8BTraining Paradigm=Generalization Across Model Families, SSP Integration=false2025.10 | 45.8 | |
| Qwen2.5-7B-InstructTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=false2025.10 | 36.4 | |
| Qwen2.5-7B-BaseTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=false2025.10 | 25 |