Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-coupled problem solving. However, mainstream in-context learning (ICL) approaches typically incorporate detailed tool documentation and usage examples directly into the context. This results in substantial inference overhead and heightened risks of hallucination as the context length grows. Conversely, while tuning-based methods improve general tool-calling capabilities, they often fail to effectively internalize the specific details of previously seen tools, thereby retaining a dependency on in-context documentation. To address these limitations, we propose ParaTool, a framework that projects each tool into a dedicated, loadable set of parameters. By equipping a dynamic integration of these parameterized tools, the LLM can perform tool calling without relying on in-context documents or examples. Specifically, our approach consists of three stages: (1) parametric tool pre-training encapsulates the knowledge of different tools into independent parameter modules; (2) soft tool selection employs a gating network to dynamically weigh and aggregate relevant tool parameters; and (3) parametric tool fine-tuning jointly updates tool parameters to align the training and inference processes. Experiments on Stable ToolBench and BFCL demonstrate that ParaTool significantly outperforms strong ICL-based baselines, achieving superior performance while reducing computational complexity.

翻译：工具调用通过支持大语言模型（LLMs）与外部可执行接口进行有根交互，从而赋能环境耦合的问题求解。然而，主流情境学习（ICL）方法通常将详尽的工具文档及使用示例直接嵌入上下文之中，这导致随着上下文长度增长而产生显著的推理开销与幻觉风险。相反，基于微调的方法虽然能提升通用工具调用能力，但往往未能有效内化先前所见工具的具体细节，从而依然依赖于上下文文档。为应对这些局限，本文提出ParaTool框架，该框架将每个工具映射为一组可独立加载的参数集合。通过动态集成这些参数化工具，LLMs可在无需上下文文档或示例的条件下执行工具调用。具体而言，本方法包含三个阶段：（1）参数化工具预训练，将不同工具的知识封装至独立参数模块中；（2）软性工具选择，采用门控网络动态加权并聚合相关工具参数；（3）参数化工具微调，联合更新工具参数以对齐训练与推理过程。在Stable ToolBench和BFCL上的实验表明，ParaTool显著优于基于ICL的强基线方法，在降低计算复杂度的同时实现了更优性能。