General Question Answering on TriviaQA (token-level F1)
76.4Token-Level F1Oracle
Evaluation Results
| Method | Links | |
|---|---|---|
| OracleMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 76.4 | |
| OracleMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 74.9 | |
| COSEARCHMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 74.7 | |
| Fixed RankerMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 73.5 | |
| Retrieval OnlyMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 72.8 | |
| COSEARCHMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 71.4 | |
| Fixed RankerMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 69.7 | |
| ZeroSearchMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 69.3 | |
| RAGMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 68.9 | |
| Search-R1Main agent backbone=Qwen2.5-7B-Instruct2026.04 | 68.1 | |
| Retrieval OnlyMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 65.1 | |
| ZeroSearchMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 64.2 | |
| Search-R1Main agent backbone=Qwen2.5-3B-Instruct2026.04 | 63.7 | |
| Search-o1Main agent backbone=Qwen2.5-7B-Instruct2026.04 | 52.6 | |
| Direct InferenceMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 50.4 | |
| Search-o1Main agent backbone=Qwen2.5-3B-Instruct2026.04 | 50.1 | |
| RAGMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 47.8 | |
| CoTMain agent backbone=Qwen2.5-7B-Instruct2026.04 | 45.6 | |
| CoTMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 36.3 | |
| Direct InferenceMain agent backbone=Qwen2.5-3B-Instruct2026.04 | 34.3 |