Learning Evolving Tools for Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915176182185984 |
|---|---|
| author | Chen, Guoxin Zhang, Zhong Cong, Xin Guo, Fangda Wu, Yesai Lin, Yankai Feng, Wenzheng Wang, Yasheng |
| author_facet | Chen, Guoxin Zhang, Zhong Cong, Xin Guo, Fangda Wu, Yesai Lin, Yankai Feng, Wenzheng Wang, Yasheng |
| contents | Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools. Existing research primarily focuses on static environments and overlooks this issue, limiting the adaptability of LLMs in real-world applications. In this paper, we propose ToolEVO, a novel framework designed to enhance the adaptive and reflective capabilities of LLMs against tool variability. By leveraging Monte Carlo Tree Search, ToolEVO facilitates active exploration and interaction of LLMs within dynamic environments, allowing for autonomous self-reflection and self-updating of tool usage based on environmental feedback. Additionally, we introduce ToolQA-D, a benchmark specifically designed to evaluate the impact of tool variability. Extensive experiments demonstrate the effectiveness and stability of our approach, highlighting the importance of adaptability to tool variability for effective tool learning. Code: https://github.com/Chen-GX/ToolEVO |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06617 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Evolving Tools for Large Language Models Chen, Guoxin Zhang, Zhong Cong, Xin Guo, Fangda Wu, Yesai Lin, Yankai Feng, Wenzheng Wang, Yasheng Computation and Language Artificial Intelligence Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools. Existing research primarily focuses on static environments and overlooks this issue, limiting the adaptability of LLMs in real-world applications. In this paper, we propose ToolEVO, a novel framework designed to enhance the adaptive and reflective capabilities of LLMs against tool variability. By leveraging Monte Carlo Tree Search, ToolEVO facilitates active exploration and interaction of LLMs within dynamic environments, allowing for autonomous self-reflection and self-updating of tool usage based on environmental feedback. Additionally, we introduce ToolQA-D, a benchmark specifically designed to evaluate the impact of tool variability. Extensive experiments demonstrate the effectiveness and stability of our approach, highlighting the importance of adaptability to tool variability for effective tool learning. Code: https://github.com/Chen-GX/ToolEVO |
| title | Learning Evolving Tools for Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.06617 |