Tool Retrieval on ToolBench In-domain (I2)
91.91NDCG@1ToolWeaver
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ToolWeaverImplementation source=This Paper2026.01 | 91.91 | 93.07 | 95.63 | |
| ToolGenImplementation source=Original2026.01 | 91.45 | 88.79 | 91.13 | |
| ToolWeaverImplementation Source=This paper2026.01 | 89.76 | 89.7 | 91.8 | |
| IterFeedbackImplementation source=Original2026.01 | 89.01 | 85.46 | 87.1 | |
| ToolGenImplementation source=Re-implemented2026.01 | 87.5 | 88.52 | 90.81 | |
| ToolGenImplementation Source=Re-implemented2026.01 | 84 | 85.65 | 89.02 | |
| ToolGenImplementation Source=Reported in Wang et al. (2024b)2026.01 | 83.46 | 86.24 | 88.84 | |
| ToolRetrieverImplementation source=Re-implemented2026.01 | 72 | 73.27 | 80.4 | |
| ToolRetrieverImplementation source=Original2026.01 | 71.18 | 64.81 | 70.35 | |
| ToolRetrieverImplementation Source=Reported in Wang et al. (2024b)2026.01 | 64.54 | 57.91 | 63.61 | |
| ToolRetrieverImplementation Source=Re-implemented2026.01 | 63 | 66.38 | 72.72 | |
| Re-InvokeImplementation source=Original2026.01 | 54.56 | — | 53.79 | |
| EmbSimImplementation source=Re-implemented2026.01 | 54 | 45.31 | 49.54 | |
| EmbSimImplementation source=Original2026.01 | 49.11 | 42.27 | 46.56 | |
| EmbSimImplementation Source=Re-implemented2026.01 | 46 | 39.58 | 43.05 | |
| EmbSimImplementation Source=Reported in Wang et al. (2024b)2026.01 | 40.84 | 36.67 | 39.55 | |
| BM25Implementation source=Re-implemented2026.01 | 26.5 | 25.97 | 27.96 | |
| BM25Implementation source=Original2026.01 | 24.13 | 25.29 | 27.65 | |
| BM25Implementation Source=Re-implemented2026.01 | 20 | 21.92 | 23.46 | |
| BM25Implementation Source=Reported in Wang et al. (2024b)2026.01 | 18.29 | 20.74 | 22.18 |