Training an LLM to call tools reliably requires datasets that pair user queries with correct tool-use chains. Producing that data at scale has been slow and expensive. A team of researchers from Google, the University of Tokyo, RIKEN AIP, and Tohoku University introduce ToolGrad. The research work inverts the usual pipeline: build a verified tool chain first, then write the query. Gemma-3 models fine-tuned on 500 samples of the resulting data reach scores that sit alongside frontier proprietary models on the Berkeley Function Calling Leaderboard.

Is it deployable? Yes. The code is Apache-2.0, the ToolGrad-500 dataset and the 1B, 4B, and 12B models are on Hugging Face, and there is a PyPI package.

The problem with query-first generation

Prior pipelines such as ToolBench and ToolACE follow a query-first recipe. The system samples a pool of APIs, asks an LLM to invent a plausible user instruction, and then dispatches a depth-first search (DFS) agent to find a tool-use path that satisfies it. The search has no guarantee of success. When it dead-ends, the compute spent on exploration is wasted, and the sample is discarded. The paper frames this as distilling valuable trajectories from a complex and often failing agent exploration, which is inherently inefficient.

ToolGrad reverses the order. It first constructs a ground-truth tool-use chain by actually executing APIs, then annotates that chain with a matching user query. An explicit, working chain is far less ambiguous than a hypothetical prompt, so the chain-to-query step takes a single LLM call.

Four modules in a loop

Each iteration runs four modules in sequence:

• API Proposer narrows a sampled set of APIs down to a few candidates that could extend the current workflow.
• API Executors run those candidates in parallel and produce detailed execution reports.
• API Selector reviews the reports, picks the single best-performing candidate, and appends it to the chain.
• Query Generator writes a user query that the completed chain is guaranteed to satisfy.