Tool Identification on In-domain (seen)
85.95Exact Match (EM)TInR-U
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TInR-U2026.04 | 85.95 | 88.38 | |
| ToolGen2026.04 | 83.78 | 86.76 | |
| TR-Feedback+ToolRLRetriever=TR-Feedback, Reasoning Model=ToolRL2026.04 | 65.41 | 72.61 | |
| ToolRetriever+Hammer2.1-7bRetriever=ToolRetriever, Reasoning Model=Hammer2.1-7b2026.04 | 63.78 | 69.46 | |
| ToolRetriever+xLAM-7b-rRetriever=ToolRetriever, Reasoning Model=xLAM-7b-r2026.04 | 63.78 | 69.46 | |
| ToolRetriever+Qwen3-8BRetriever=ToolRetriever, Reasoning Model=Qwen3-8B2026.04 | 63.78 | 69.46 | |
| ToolRetriever+ToolRLRetriever=ToolRetriever, Reasoning Model=ToolRL2026.04 | 63.78 | 69.46 | |
| Ada-embedding+ToolRLRetriever=Ada-embedding, Reasoning Model=ToolRL2026.04 | 56.22 | 61.71 | |
| BM25+ToolRLRetriever=BM25, Reasoning Model=ToolRL2026.04 | 48.11 | 54.68 |