Advancing and Benchmarking Personalized Tool Invocation for LLMs

ICLR 2026 Conference Submission17112 Authors

Keywords: Large Language Models, Tool Learning, Personalization, Benchmarking

Abstract: Tool invocation is a crucial mechanism for extending the capabilities of Large Language Models (LLMs) and has recently garnered significant attention. It enables LLMs to solve complex problems through tool calls while accessing up-to-date world knowledge. However, existing work primarily focuses on the fundamental ability of LLMs to invoke tools for problem-solving, without considering personalized constraints in tool invocation. In this work, we introduce the concept of Personalized Tool Invocation and define two key tasks: Tool Personalization and Parameter Personalization. Tool Personalization addresses user preferences when selecting among functionally similar tools, while Parameter Personalization considers cases where a user query lacks certain tool parameters, requiring the model to infer them from the user profile. To tackle these challenges, we propose PTool, a data synthesis framework designed for personalized tool invocation. Additionally, we construct PTBench, the first benchmark to evaluate personalized tool invocation. We then fine-tune various open-source models, demonstrating the effectiveness of our framework and providing valuable insights. Our model, training data, and the benchmark will be publicly released upon acceptance.

Primary Area: datasets and benchmarks

Submission Number: 17112