Multi-hop Question Answering on 2WikiMultiHopQA in-domain (test)
69.8Accuracy (Response)DLLM-Searcher
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DLLM-SearcherCategory=dLLMs Agent, paradigm=P-ReAct, training=VRPO, backbone=SDAR2026.02 | 69.8 | 64.6 | |
| R1SearcherCategory=ARM-based LLMs Agent, setup=modified (5.1.3), search_mode=best of local/Google search2026.02 | 59.6 | 63.4 | |
| WebSailorCategory=ARM-based LLMs Agent, setup=modified (5.1.3), tools=search only2026.02 | 59.4 | 61.4 | |
| ReARTeRCategory=Traditional RAG2026.02 | 55.4 | 53.4 | |
| CR-PlannerCategory=Traditional RAG2026.02 | 48.2 | 22 | |
| Search-o1Category=ARM-based LLMs Agent2026.02 | 47 | 51.2 | |
| Search-R1Category=ARM-based LLMs Agent2026.02 | 46 | 50 | |
| LLaDACategory=dLLMs Agent, paradigm=ReAct, acceleration=Fast-dLLM2026.02 | 42 | 38.8 | |
| IRCoTCategory=Traditional RAG2026.02 | 41 | 38.6 | |
| Iter-RetGenCategory=Traditional RAG2026.02 | 32.4 | 34.4 | |
| Adaptive-RAGCategory=Traditional RAG2026.02 | 27.8 | 25.8 | |
| Selective-ContextCategory=Traditional RAG2026.02 | 27.4 | 29.6 | |
| SuReCategory=Traditional RAG2026.02 | 22.2 | 26.8 | |
| DreamCategory=dLLMs Agent, paradigm=ReAct, acceleration=Fast-dLLM2026.02 | 13.6 | 12 |