『Google — Beating Your Own Teacher at Tool Use』のカバーアート

Google — Beating Your Own Teacher at Tool Use

Google — Beating Your Own Teacher at Tool Use

無料で聴く

ポッドキャストの詳細を見る

【Amazonプライム会員限定】今ならプレミアムプランが4か月 月額99円。

10月19日まで。※適用条件あり
A deep dive into how Google Research flipped the standard recipe for training AI models to use tools and APIs. Instead of writing a user question first and then struggling to find a matching chain of tool calls that answers it — which fails constantly once you're picking from thousands of real APIs — their ToolGrad system builds a verified, working tool-call workflow first, using an iterative loop that treats an AI critic's plain-language feedback as a steering signal (borrowed from a technique called "textual gradients"), and only then writes the question that workflow answers. We cover the business problem (query-first data generation wastes enormous effort on unanswerable or unverifiable examples), the technical approach (a four-step propose-execute-select-update loop building tool-call chains from a catalog of 16,000+ real APIs), and the standout result: a fine-tuned 12-billion-parameter model trained on this data scored competitively with Gemini 2.5 Pro and Claude 4.5 Opus on a leading function-calling benchmark — and notably outperformed the very model that generated its own training data. Source article: "ToolGrad: Efficient Tool-Use Dataset Generation with Textual 'Gradients'" — Google Research, https://research.google/blog/toolgrad-efficient-tool-use-dataset-generation-with-textual-gradients/ (published 2026-09).
adbl_web_anon_alc_button_suppression_t1
まだレビューはありません