arXivPaperNeeds Review
MidTool: Mid-training Data Synthesis for Agentic Tool Use
MidTool trains general tool use before post-training, using API, MCP, document, web, PDF, and code data. Qwen3 4B and 8B variants improved across three downstream tool-use benchmarks.
arXiv
Source Summary
MidTool builds an open mid-training corpus from web, PDF, and code data plus real-world APIs, MCP skills, and document-grounded workflows. It targets tool selection, argument grounding, workflow composition, and incomplete information.
Practical Implication
The authors mid-trained **Qwen3-4B-Base** and **Qwen3-8B-Base**, then applied both supervised fine-tuning and reinforcement learning. Builders training agent models should consider tool competence a dedicated training stage rather than only a post-training behavior.
Agent-Ready Context
MidTool builds an open mid-training corpus from web, PDF, and code data plus real-world APIs, MCP skills, and document-grounded workflows. It targets tool selection, argument grounding, workflow composition, and incomplete information. The authors mid-trained **Qwen3-4B-Base** and **Qwen3-8B-Base**, then applied both supervised fine-tuning and reinforcement learning. Builders training agent models should consider tool competence a dedicated training stage rather than only a post-training behavior. MidTool-Mix improved results under SFT and RL on **BFCL, tau2-Bench, and MCP Universe**, but the supplied material gives no effect sizes. The evidence is also limited to two sizes from one model family.
Context Map
modelresearchcoding#tool-use#mcp#agent-sdksUncertainty
MidTool-Mix improved results under SFT and RL on **BFCL, tau2-Bench, and MCP Universe**, but the supplied material gives no effect sizes. The evidence is also limited to two sizes from one model family.