Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2508.12725 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908493009649664 |
|---|---|
| author | Chen, Wenjie Li, Wenbin Yao, Di Meng, Xuying Gong, Chang Bi, Jingping |
| author_facet | Chen, Wenjie Li, Wenbin Yao, Di Meng, Xuying Gong, Chang Bi, Jingping |
| contents | Tool planning with large language models (LLMs), referring to selecting, organizing, and preparing the tools necessary to complete a user request, bridges the gap between natural language understanding and task execution. However, current works treat different tools as isolated components and fail to leverage the inherent dependencies of tools, leading to invalid planning results. Since tool dependencies are often incomplete, it becomes challenging for LLMs to accurately identify the appropriate tools required by a user request, especially when confronted with a large toolset. To solve this challenge, we propose \texttt{GTool}, which is the first work aiming to enhance the tool planning ability of LLMs under incomplete dependencies. \texttt{GTool} constructs a request-specific tool graph to select tools efficiently and generate the \texttt{<graph token>} which provides sufficient dependency information understandable by LLMs. Moreover, a missing dependency prediction task is designed to improve the reliability of \texttt{GTool} with incomplete dependencies. Without trimming LLMs, \texttt{GTool} can be seamlessly integrated with various LLM backbones without extensive retraining. Extensive experiments show that \texttt{GTool} achieves more than 29.6\% performance improvements compared with the state-of-the-art (SOTA) baselines with a light-weight (7B) LLM backbone. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GTool: Graph Enhanced Tool Planning with Large Language Model Chen, Wenjie Li, Wenbin Yao, Di Meng, Xuying Gong, Chang Bi, Jingping Artificial Intelligence Tool planning with large language models (LLMs), referring to selecting, organizing, and preparing the tools necessary to complete a user request, bridges the gap between natural language understanding and task execution. However, current works treat different tools as isolated components and fail to leverage the inherent dependencies of tools, leading to invalid planning results. Since tool dependencies are often incomplete, it becomes challenging for LLMs to accurately identify the appropriate tools required by a user request, especially when confronted with a large toolset. To solve this challenge, we propose \texttt{GTool}, which is the first work aiming to enhance the tool planning ability of LLMs under incomplete dependencies. \texttt{GTool} constructs a request-specific tool graph to select tools efficiently and generate the \texttt{<graph token>} which provides sufficient dependency information understandable by LLMs. Moreover, a missing dependency prediction task is designed to improve the reliability of \texttt{GTool} with incomplete dependencies. Without trimming LLMs, \texttt{GTool} can be seamlessly integrated with various LLM backbones without extensive retraining. Extensive experiments show that \texttt{GTool} achieves more than 29.6\% performance improvements compared with the state-of-the-art (SOTA) baselines with a light-weight (7B) LLM backbone. |
| title | GTool: Graph Enhanced Tool Planning with Large Language Model |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.12725 |