ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

2025-05-12

AI Summary

Current LLM tool-use capabilities rely heavily on expensive high-end models for synthetic data generation, leading to prohibitive costs, knowledge-domain mismatch, and poor compatibility of synthetic data. Method: This paper proposes a lightweight self-improving framework—“Goal Decomposition–Self-Evolving Collaboration”—featuring (i) a novel goal decomposition mechanism for tool learning, (ii) a self-evolving training paradigm that eliminates reliance on advanced models, and (iii) integrated techniques for task decomposition, cross-architecture adaptation, and synthetic-data consistency constraints. Contribution/Results: The framework significantly improves tool-call accuracy and generalization across multi-scale and heterogeneous model architectures. It reduces high-end model invocation costs by over 90%, effectively mitigates knowledge-domain mismatch, and establishes a new pathway for autonomous, resource-efficient evolution of tool-use capabilities in lightweight LLMs.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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 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.

Problem

• Reducing reliance on advanced LLMs for tool learning
• Addressing data compatibility issues in tool-using models
• Enhancing tool-making and tool-using abilities via decomposition

Innovation

• Decomposes tool-learning into sub-tasks
• Introduces self-evolving paradigm for models
• Reduces reliance on advanced LLMs