Zhongyi Zhou and colleagues · Tool-Use Data Generation

ToolGrad

Generates tool-use training data through an iterative API proposer and executor loop that refines text the way gradient descent refines weights, with MCP backends supported and a quick-start demo needing only a Gemini API key and no GPU. Ships three fine-tuned models at 1B, 4B and 12B built on Gemma 3, evaluated on the Berkeley Function Calling Leaderboard, plus the ToolGrad-500 dataset. ACL 2026 Findings, Apache-2.0, with code, models and data all released.