{"ID":2899509,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00487","arxiv_id":"2507.00487","title":"MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models","abstract":"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.","short_abstract":"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 represent...","url_abs":"https://arxiv.org/abs/2507.00487","url_pdf":"https://arxiv.org/pdf/2507.00487v2","authors":"[\"Jianghao Lin\",\"Xinyuan Wang\",\"Xinyi Dai\",\"Menghui Zhu\",\"Bo Chen\",\"Ruiming Tang\",\"Yong Yu\",\"Weinan Zhang\"]","published":"2025-07-01T07:02:26Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":612489,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2899509,"paper_url":"https://arxiv.org/abs/2507.00487","paper_title":"MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models","repo_url":"https://github.com/wxydada/MassTool","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}