Large Language Models as Tool Makers Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou Paper link Motivation Recent research shows the potential of enhancing the problem-solving ability of large language models (LLMs) through the use of external tools. However, prior work along this line depends on the availability of existing tools. In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs A s Tool M akers (LATM), where LLMs create their own reusable tools for problem-solving.
| Stars | 1,058 |
| Forks | 96 |
| Language | Jupyter Notebook |
| Category | LLM 插件 |
| Quality Score | 22.45/100 |
| Open Issues | 4 |
| Last Updated | 2023-05-29 |
| Created | 2023-05-25 |
| Est. Tokens | ~93k |
Explore other popular llm 插件 tools:
LLM-ToolMaker is an open-source llm 插件 by ctlllll with 1.1k GitHub stars.
LLM-ToolMaker is primarily written in Jupyter Notebook.
You can find installation instructions and usage details in the LLM-ToolMaker GitHub repository at github.com/ctlllll/LLM-ToolMaker. The project has 1.1k stars and 96 forks, indicating an active community.