From the source
Google Research introduces ToolGrad, a data generation framework that reverses the traditional paradigm by first generating tool-use answers before user queries, enabling LLMs to achieve better tool-use performance.
- The framework was presented at ACL 2026.
- Experiments show that fine-tuning Gemma-3 models on ToolGrad-500 data improves tool-use performance across all tested parameter sizes, with ToolGrad-12B achieving a score of 83.1 on the Berkeley Function Calling Leaderboard.
