Multi-hop Question Answering on HotpotQA in-domain (test)
60.4ACC_RDLLM-Searcher
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DLLM-SearcherCategory=dLLMs Agent, paradigm=P-ReAct, training=VRPO, backbone=SDAR, block_size=1282026.02 | 60.4 | 62.4 | |
| R1SearcherCategory=ARM-based LLMs Agent, setup=modified (5.1.3), search_mode=best of local/Google search2026.02 | 58 | 62.2 | |
| WebSailorCategory=ARM-based LLMs Agent, setup=modified (5.1.3), tools=search only2026.02 | 50.4 | 52.4 | |
| Search-R1Category=ARM-based LLMs Agent2026.02 | 49.6 | 62.2 | |
| IRCoTCategory=Traditional RAG2026.02 | 48.8 | 55.2 | |
| ReARTeRCategory=Traditional RAG2026.02 | 46.8 | 50.6 | |
| CR-PlannerCategory=Traditional RAG2026.02 | 44.4 | 33.6 | |
| Iter-RetGenCategory=Traditional RAG2026.02 | 41.6 | 54.4 | |
| Search-o1Category=ARM-based LLMs Agent2026.02 | 40.8 | 53.2 | |
| Adaptive-RAGCategory=Traditional RAG2026.02 | 38 | 47.4 | |
| LLaDACategory=dLLMs Agent, paradigm=ReAct, acceleration=Fast-dLLM2026.02 | 36 | 32.8 | |
| Selective-ContextCategory=Traditional RAG2026.02 | 33.2 | 43.4 | |
| SuReCategory=Traditional RAG2026.02 | 32.4 | 48.4 | |
| DreamCategory=dLLMs Agent, paradigm=ReAct, acceleration=Fast-dLLM2026.02 | 11 | 11.6 |