ToolDev: Self-Improving Tool Learning via Decomposition and Evolution

ACL ARR 2025 February Submission6833 Authors

Abstract:

The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data synthesis. However, this method incurs significant costs associated with advanced model usage and often results in data compatibility issues, led by the high discrepancy in the knowledge scope between the advanced model and the target model.
To address these challenges, we propose ToolDev, a self-improving framework for tool learning. First, we decompose the tool-learning objective into sub-tasks that enhance basic tool-making and tool-using abilities. Then, we introduce a self-evolving paradigm that allows lightweight models to self-improve, reducing reliance on advanced LLMs. Extensive experiments validate the effectiveness of our approach across models of varying scales and architectures.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: NLP Applications, Language Modeling, Generation, Question Answering

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 6833