Tool-augmented large language models (LLMs) may need to forget learned tools due to security concerns, privacy restrictions, or deprecated tools. However, ``tool unlearning'' has not been investigated in machine unlearning literature. We introduce this novel task, which requires addressing distinct challenges compared to traditional unlearning: knowledge removal rather than forgetting individual samples, the high cost of optimizing LLMs, and the need for principled evaluation metrics. To bridge these gaps, we propose ToolDelete , the first approach for unlearning tools from tool-augmented LLMs which implements three properties for effective tool unlearning, and a new membership inference attack (MIA) model for evaluation. Experiments on three tool learning datasets and tool-augmented LLMs show that ToolDelete effectively unlearns both randomly selected and category-specific tools, while preserving the LLM's knowledge on non-deleted tools and maintaining performance on general tasks.

We study the problem of forgetting non-trustworthy tools from LLMs that know how to use tools. We propose an effective method and compare to baselines on three benchmarks.