Question Answering on SimpleQA out-domain (test)
36.5LasJD2PLAN-7B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| D2PLAN-7BBase LLM=Qwen2.5-7B-Instruct2026.01 | 36.5 | 27.5 | — | |
| AutoRefineBase LLM=Qwen2.5-3B-Instruct2026.01 | 36.2 | 24.9 | — | |
| ReSearchBase LLM=Qwen2.5-7B-Instruct2026.01 | 36.2 | 27.3 | — | |
| StepSearchBase LLM=Qwen2.5-7B-Instruct2026.01 | 34.8 | 24.9 | — | |
| R1-SearcherBase LLM=Qwen2.5-7B-Instruct2026.01 | 34.6 | 25.6 | — | |
| Search-R1Base LLM=Qwen2.5-7B-Instruct2026.01 | 34.4 | 23.1 | — | |
| D2PLAN-3BBase LLM=Qwen2.5-3B-Instruct2026.01 | 34.1 | 25.5 | — | |
| ZeroSearchBase LLM=Qwen2.5-7B-Instruct2026.01 | 33.1 | 24.1 | — | |
| ZeroSearchBase LLM=Qwen2.5-3B-Instruct2026.01 | 31.5 | 22.8 | — | |
| StepSearchBase LLM=Qwen2.5-3B-Instruct2026.01 | 28.2 | 20.4 | — | |
| Search-R1Base LLM=Qwen2.5-3B-Instruct2026.01 | 17.7 | 8.2 | — | |
| A-Mem2026.04 | — | — | 38.8 | |
| ExpeL2026.04 | — | — | 43 | |
| Mem02026.04 | — | — | 38.1 | |
| Memento2026.04 | — | — | 42.4 | |
| MIAvariant=Unsupervised2026.04 | — | — | 46.6 | |
| MIAvariant=Standard2026.04 | — | — | 47.7 | |
| No Memory2026.04 | — | — | 40.7 | |
| RAG2026.04 | — | — | 38.3 | |
| ReasoningBank2026.04 | — | — | 42.4 |