Tool Learning on RestBench Spotify
87.72SuccessToolCoder
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ToolCoderBackbone=gpt-4o-mini, Paradigm=Code-based2025.02 | 87.72 | 78.95 | |
| ToolCoder w/o Reusable RepositoryBackbone=gpt-4o-mini, Paradigm=Code-based, Reusable Repository=false2025.02 | 78.95 | 71.93 | |
| ToolCoder w/o Error ReflectionBackbone=gpt-4o-mini, Paradigm=Code-based, Error Reflection=false2025.02 | 73.68 | 70.18 | |
| CodeActBackbone=gpt-4o-mini, Paradigm=Code-based2025.02 | 71.93 | 66.67 | |
| ChameleonBackbone=gpt-4o-mini, Paradigm=Text-based2025.02 | 70.18 | 63.16 | |
| ReActBackbone=gpt-4o-mini, Paradigm=Text-based2025.02 | 68.42 | 52.63 | |
| ATCBackbone=gpt-4o-mini, Paradigm=Code-based2025.02 | 65.47 | 68.42 | |
| ConAgentsBackbone=gpt-4o-mini, Paradigm=Text-based2025.02 | 64.92 | 68.42 | |
| EasyToolBackbone=gpt-4o-mini, Paradigm=Text-based2025.02 | 62.19 | 64.92 | |
| RestGPTBackbone=gpt-4o-mini, Paradigm=Text-based2025.02 | 61.41 | 57.89 |