Multi-hop Question Answering on Musique in-domain (test)
29.6Accuracy RReARTeR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ReARTeRCategory=Traditional RAG2026.02 | 29.6 | 30.2 | |
| DLLM-SearcherCategory=dLLMs Agent, paradigm=P-ReAct, training=VRPO, backbone=SDAR2026.02 | 29 | 29.8 | |
| R1SearcherCategory=ARM-based LLMs Agent, setup=modified (5.1.3), search_mode=best of local/Google search2026.02 | 28.2 | 31.4 | |
| Search-R1Category=ARM-based LLMs Agent2026.02 | 28 | 26 | |
| WebSailorCategory=ARM-based LLMs Agent, setup=modified (5.1.3), tools=search only2026.02 | 22 | 28 | |
| Search-o1Category=ARM-based LLMs Agent2026.02 | 15.2 | 19 | |
| LLaDACategory=dLLMs Agent, paradigm=ReAct, acceleration=Fast-dLLM2026.02 | 15.2 | 15.8 | |
| Iter-RetGenCategory=Traditional RAG2026.02 | 14.8 | 18.2 | |
| CR-PlannerCategory=Traditional RAG2026.02 | 12.2 | 11.4 | |
| IRCoTCategory=Traditional RAG2026.02 | 11.6 | 15.8 | |
| SuReCategory=Traditional RAG2026.02 | 7.2 | 10 | |
| Adaptive-RAGCategory=Traditional RAG2026.02 | 7.2 | 11.6 | |
| Selective-ContextCategory=Traditional RAG2026.02 | 5.8 | 8.8 | |
| DreamCategory=dLLMs Agent, paradigm=ReAct, acceleration=Fast-dLLM2026.02 | 3.8 | 3.2 |