MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models
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_ | 1866908429849722880 |
|---|---|
| author | Lin, Jianghao Wang, Xinyuan Dai, Xinyi Zhu, Menghui Chen, Bo Tang, Ruiming Yu, Yong Zhang, Weinan |
| author_facet | Lin, Jianghao Wang, Xinyuan Dai, Xinyi Zhu, Menghui Chen, Bo Tang, Ruiming Yu, Yong Zhang, Weinan |
| contents | Tool retrieval is a critical component in enabling large language models (LLMs) to interact effectively with external tools. It aims to precisely filter the massive tools into a small set of candidates for the downstream tool-augmented LLMs. However, most existing approaches primarily focus on optimizing tool representations, often neglecting the importance of precise query comprehension. To address this gap, we introduce MassTool, a multi-task search-based framework designed to enhance both query representation and tool retrieval accuracy. MassTool employs a two-tower architecture: a tool usage detection tower that predicts the need for function calls, and a tool retrieval tower that leverages a query-centric graph convolution network (QC-GCN) for effective query-tool matching. It also incorporates search-based user intent modeling (SUIM) to handle diverse and out-of-distribution queries, alongside an adaptive knowledge transfer (AdaKT) module for efficient multi-task learning. By jointly optimizing tool usage detection loss, list-wise retrieval loss, and contrastive regularization loss, MassTool establishes a robust dual-step sequential decision-making pipeline for precise query understanding. Extensive experiments demonstrate its effectiveness in improving retrieval accuracy. Our code is available at https://github.com/wxydada/MassTool. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00487 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models Lin, Jianghao Wang, Xinyuan Dai, Xinyi Zhu, Menghui Chen, Bo Tang, Ruiming Yu, Yong Zhang, Weinan Information Retrieval Computation and Language Tool retrieval is a critical component in enabling large language models (LLMs) to interact effectively with external tools. It aims to precisely filter the massive tools into a small set of candidates for the downstream tool-augmented LLMs. However, most existing approaches primarily focus on optimizing tool representations, often neglecting the importance of precise query comprehension. To address this gap, we introduce MassTool, a multi-task search-based framework designed to enhance both query representation and tool retrieval accuracy. MassTool employs a two-tower architecture: a tool usage detection tower that predicts the need for function calls, and a tool retrieval tower that leverages a query-centric graph convolution network (QC-GCN) for effective query-tool matching. It also incorporates search-based user intent modeling (SUIM) to handle diverse and out-of-distribution queries, alongside an adaptive knowledge transfer (AdaKT) module for efficient multi-task learning. By jointly optimizing tool usage detection loss, list-wise retrieval loss, and contrastive regularization loss, MassTool establishes a robust dual-step sequential decision-making pipeline for precise query understanding. Extensive experiments demonstrate its effectiveness in improving retrieval accuracy. Our code is available at https://github.com/wxydada/MassTool. |
| title | MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2507.00487 |