GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909503113396224 |
|---|---|
| author | Luo, Jianwen Huang, Yiming Meng, Jinxiang Lei, Fangyu He, Shizhu Liu, Xiao Jiang, Shanshan Dong, Bin Zhao, Jun Liu, Kang |
| author_facet | Luo, Jianwen Huang, Yiming Meng, Jinxiang Lei, Fangyu He, Shizhu Liu, Xiao Jiang, Shanshan Dong, Bin Zhao, Jun Liu, Kang |
| contents | Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE (Graph-based Adaptive Tool Evolution), an adaptive framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios. We evaluate GATE on open-ended tasks (Minecraft), agent-based tasks (TextCraft, DABench), and code generation tasks (MATH, Date, TabMWP). Our results show that GATE achieves up to 4.3x faster milestone completion in Minecraft compared to the previous SOTA, and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks. GATE demonstrates the power of adaptive evolution, balancing tool quantity, complexity, and functionality while maintaining high efficiency. Code and data are available at \url{https://github.com/ayanami2003/GATE}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14848 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks Luo, Jianwen Huang, Yiming Meng, Jinxiang Lei, Fangyu He, Shizhu Liu, Xiao Jiang, Shanshan Dong, Bin Zhao, Jun Liu, Kang Computation and Language 68T50 I.2.7 Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE (Graph-based Adaptive Tool Evolution), an adaptive framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios. We evaluate GATE on open-ended tasks (Minecraft), agent-based tasks (TextCraft, DABench), and code generation tasks (MATH, Date, TabMWP). Our results show that GATE achieves up to 4.3x faster milestone completion in Minecraft compared to the previous SOTA, and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks. GATE demonstrates the power of adaptive evolution, balancing tool quantity, complexity, and functionality while maintaining high efficiency. Code and data are available at \url{https://github.com/ayanami2003/GATE}. |
| title | GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks |
| topic | Computation and Language 68T50 I.2.7 |
| url | https://arxiv.org/abs/2502.14848 |