Tool calling has become increasingly popular for Large Language Models (LLMs). However, for large tool sets, the resulting tokens would exceed the LLM's context window limit, making it impossible to include every tool. Hence, an external retriever is used to provide LLMs with the most relevant tools for a query. Existing retrieval models rank tools based on the similarity between a user query and a tool description (TD). This leads to suboptimal retrieval as user requests are often poorly aligned with the language of TD. To remedy the issue, we propose ToolDreamer, a framework to condition retriever models to fetch tools based on hypothetical (synthetic) TD generated using an LLM, i.e., description of tools that the LLM feels will be potentially useful for the query. The framework enables a more natural alignment between queries and tools within the language space of TD's. We apply ToolDreamer on the ToolRet dataset and show that our method improves the performance of sparse and dense retrievers with and without training, thus showcasing its flexibility. Through our proposed framework, our aim is to offload a portion of the reasoning burden to the retriever so that the LLM may effectively handle a large collection of tools without inundating its context window.

翻译：工具调用在大语言模型（LLM）中的应用日益广泛。然而，对于大规模工具集，其对应的令牌数量可能超出LLM的上下文窗口限制，导致无法包含所有工具。因此，通常需要借助外部检索器为LLM提供与查询最相关的工具。现有检索模型主要依据用户查询与工具描述（TD）之间的相似度对工具进行排序。由于用户请求往往与TD的语言表述存在偏差，这种检索方式常导致次优结果。为解决该问题，我们提出ToolDreamer框架，该框架通过基于LLM生成的假设性（合成）TD来调节检索器模型，即LLM认为可能对查询有用的工具描述。该框架能够在TD的语言空间内实现查询与工具之间更自然的对齐。我们在ToolRet数据集上应用ToolDreamer，结果表明该方法能提升稀疏与稠密检索器在训练/非训练场景下的性能，展现了其灵活性。通过所提出的框架，我们的目标是将部分推理负担转移至检索器，使LLM能够有效处理大规模工具集合，同时避免上下文窗口过载。