让小模型通过分解任务自我进化，提升工具使用能力。
ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
- 将工具学习拆解为基础工具制作与使用子任务
- 小模型可自主进化，减少对大模型依赖
- 适用于不同规模和架构的模型，效果稳定
大型语言模型（LLMs）的工具使用能力使其能够获取最新外部信息并处理复杂任务。当前增强该能力的方法主要依赖于通过数据合成来蒸馏高级模型，但这种方法不仅消耗大量高级模型资源，还常因高级模型与目标模型知识范围差异过大而导致数据不兼容问题。为此，我们提出 ToolACE-DEV，一种自改进的工具学习框架。首先，将工具学习目标分解为提升基础工具制作与使用能力的子任务；其次，引入自演化范式，使轻量级模型能够自主优化，降低对高级 LLM 的依赖。大量实验验证了该方法在不同规模和架构模型上的有效性。
原文摘要 · Abstract (English)
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 ToolACE-DEV, 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。