用真实工具接口合成数据，提升大模型的通用工具使用能力。
MidTool: Mid-training Data Synthesis for Agentic Tool Use
- 结合网页、PDF、代码与真实工具接口生成训练数据
- 在多个评测集上显著提升模型工具调用性能
- 适合需要构建智能代理的开发者与研究者
中段训练正成为塑造大语言模型能力的关键阶段。已有研究证明，针对性中段训练可增强数学、科学等推理能力，并提升软件工程场景中的代理能力。本文探讨了尚未被充分研究的代理能力：通用工具使用。我们提出MidTool，一个面向代理工具使用中段训练的开放语料库构建管道，融合大规模网页、PDF和代码数据，以及来自真实工具API、MCP技能和文档驱动工作流的合成监督信号。MidTool旨在教会模型识别工具功能、从上下文提取参数、组合工具调用流程并处理信息缺失。我们在MidTool-Mix数据集上对Qwen3-4B-Base和Qwen3-8B-Base进行中段训练，随后通过监督微调和强化学习进行后续训练。相比基线方法，MidTool-Mix在BFCL、tau2-Bench和MCP Universe等多个下游任务上，无论采用SFT还是RL，均持续提升表现。结果表明，通用工具使用能力同样受益于专门的中段训练，而非仅依赖后训练。
原文摘要 · Abstract (English)
Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted mid-training can strengthen reasoning-intensive abilities such as math and science, and can also improve agentic capabilities in software-engineering settings. In this work, we study the parallel but less explored agentic capability: general tool use. We present MidTool, an open corpus construction pipeline for agentic tool-use mid-training that combines large-scale web, PDF, and code data with synthesized supervision from real-world tool APIs, MCP skills, and document-grounded workflows. MidTool is designed to teach models how to recognize tool affordances, ground arguments from context, compose tool call workflow, and recover from incomplete information. We mid-train Qwen3-4B-Base and Qwen3-8B-Base on MidTool-Mix, and then apply follow-up post-training with both supervised fine-tuning and reinforcement learning. Compared with baselines, MidTool-Mix consistently improves downstream performance under both SFT and RL on BFCL, tau2-Bench, and MCP Universe. These results suggest that general tool use, like other important LLM capabilities, benefits from dedicated mid-training rather than being left entirely to post-training.
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。