CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models
Submission Type: Regular Long Paper
Submission Track: Language Modeling and Analysis of Language Models
Keywords: Large Language Models, Tool Creation, Model Reasoning
TL;DR: We propose CREATOR, a framework enabling Large Language Models to create their own tools for improved performance by disentangling their abstract and concrete reasoning capabilities.
Abstract: Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math competition problems and diverse tabular contents. Remarkably, CREATOR outperforms existing chain-of-thought, program-of-thought, and tool-using baselines. Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs' tool creation ability. Further research demonstrates that leveraging LLMs as tool creators facilitates knowledge transfer, and LLMs exhibit varying levels of tool creation abilities, enabling them to adapt to diverse situations. The tool creation ability revolutionizes the LLM's problem-solving paradigm, driving us closer to the next frontier of artificial intelligence.
Submission Number: 783
Loading