让工具接口适应小模型，而非让小模型适应接口，提升工具使用准确率。
Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models
- 通过预训练熟悉度信号重命名工具组件，使接口名更符合小模型认知
- 在两个基准上工具调用准确率提升最高17%，错误率降低80%
- 无需训练即可优化，适合资源有限的部署场景
小语言模型（SLMs）在多智能体系统中可实现可扩展的工具增强，但其在工具选择和参数识别方面表现不佳。主要问题在于‘模式错配’：模型会虚构不存在于给定工具模式中的合理名称，这是由于预训练中内化的命名习惯差异所致。我们提出不训练模型适应陌生模式，而是将工具模式调整为与模型预训练知识对齐。引入无需训练的PA-Tool方法，利用峰值度（peakedness）——一种用于污染检测的信号——来识别预训练中熟悉的命名模式。通过生成多个候选名称并选择峰值度最高的，实现命名对齐。在MetaTool和RoTBench上的实验显示，准确率最高提升17%，模式错配错误减少80%。该方法无需重训练，显著提升资源效率型模型的工具使用能力。代码已开源。
原文摘要 · Abstract (English)
Small language models (SLMs) enable scalable tool-augmented multi-agent systems where multiple SLMs handle subtasks orchestrated by a powerful coordinator. However, they struggle with tool-use tasks, particularly in selecting appropriate tools and identifying correct parameters. A common failure mode is \textit{schema misalignment}: models hallucinate plausible tool names that are absent from the provided tool schema, due to different naming conventions internalized during pretraining. Rather than training models to adapt to unfamiliar schemas, we propose adapting schemas to align with models' pretrained knowledge. We introduce \textbf{PA-Tool} (Pretraining-Aligned Tool Schema Generation), a training-free method that leverages peakedness, a signal used in contamination detection that indicates pretraining familiarity, to rename tool components. By generating multiple candidates and selecting the candidate with the highest peakedness, PA-Tool identifies pretraining-aligned naming patterns. Experiments on MetaTool and RoTBench show improvements of up to 17\%, with schema misalignment errors reduced by 80\%. PA-Tool enables small models to substantially improve tool-use accuracy without retraining, showing that schema-level interventions can unlock the tool-use potential of resource-efficient models. Our code is available at https://github.com/holi-lab/PA-Tool.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。