From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
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_ | 1866929732118904832 |
|---|---|
| author | Qu, Changle Dai, Sunhao Wei, Xiaochi Cai, Hengyi Wang, Shuaiqiang Yin, Dawei Xu, Jun Wen, Ji-Rong |
| author_facet | Qu, Changle Dai, Sunhao Wei, Xiaochi Cai, Hengyi Wang, Shuaiqiang Yin, Dawei Xu, Jun Wen, Ji-Rong |
| contents | Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a crucial role by providing usage instructions for LLMs, thereby facilitating effective tool utilization. This paper concentrates on the critical challenge of bridging the comprehension gap between LLMs and external tools due to the inadequacies and inaccuracies inherent in existing human-centric tool documentation. We propose a novel framework, DRAFT, aimed at Dynamically Refining tool documentation through the Analysis of Feedback and Trials emanating from LLMs' interactions with external tools. This methodology pivots on an innovative trial-and-error approach, consisting of three distinct learning phases: experience gathering, learning from experience, and documentation rewriting, to iteratively enhance the tool documentation. This process is further optimized by implementing a diversity-promoting exploration strategy to ensure explorative diversity and a tool-adaptive termination mechanism to prevent overfitting while enhancing efficiency. Extensive experiments on multiple datasets demonstrate that DRAFT's iterative, feedback-based refinement significantly ameliorates documentation quality, fostering a deeper comprehension and more effective utilization of tools by LLMs. Notably, our analysis reveals that the tool documentation refined via our approach demonstrates robust cross-model generalization capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08197 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions Qu, Changle Dai, Sunhao Wei, Xiaochi Cai, Hengyi Wang, Shuaiqiang Yin, Dawei Xu, Jun Wen, Ji-Rong Computation and Language Artificial Intelligence Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a crucial role by providing usage instructions for LLMs, thereby facilitating effective tool utilization. This paper concentrates on the critical challenge of bridging the comprehension gap between LLMs and external tools due to the inadequacies and inaccuracies inherent in existing human-centric tool documentation. We propose a novel framework, DRAFT, aimed at Dynamically Refining tool documentation through the Analysis of Feedback and Trials emanating from LLMs' interactions with external tools. This methodology pivots on an innovative trial-and-error approach, consisting of three distinct learning phases: experience gathering, learning from experience, and documentation rewriting, to iteratively enhance the tool documentation. This process is further optimized by implementing a diversity-promoting exploration strategy to ensure explorative diversity and a tool-adaptive termination mechanism to prevent overfitting while enhancing efficiency. Extensive experiments on multiple datasets demonstrate that DRAFT's iterative, feedback-based refinement significantly ameliorates documentation quality, fostering a deeper comprehension and more effective utilization of tools by LLMs. Notably, our analysis reveals that the tool documentation refined via our approach demonstrates robust cross-model generalization capabilities. |
| title | From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.08197 |