From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs
This work addresses the challenge of improving LLMs' ability to handle complicated real-life user queries through tool usage, which is an incremental advancement in the field of AI and tool-augmented models.
The authors tackled the problem of enhancing large language models (LLMs) for complex tasks by enabling them to use external tools, specifically real-world APIs, and introduced a novel pipeline called Sum2Act that mimics human problem-solving by summarizing results and determining actions. Empirical evaluations on the ToolBench benchmark showed significant performance improvements, outperforming established methods like ReAct and DFSDT.
The distinction between humans and animals lies in the unique ability of humans to use and create tools. Tools empower humans to overcome physiological limitations, fostering the creation of magnificent civilizations. Similarly, enabling foundational models like Large Language Models (LLMs) with the capacity to learn external tool usage may serve as a pivotal step toward realizing artificial general intelligence. Previous studies in this field have predominantly pursued two distinct approaches to augment the tool invocation capabilities of LLMs. The first approach emphasizes the construction of relevant datasets for model fine-tuning. The second approach, in contrast, aims to fully exploit the inherent reasoning abilities of LLMs through in-context learning strategies. In this work, we introduce a novel tool invocation pipeline designed to control massive real-world APIs. This pipeline mirrors the human task-solving process, addressing complicated real-life user queries. At each step, we guide LLMs to summarize the achieved results and determine the next course of action. We term this pipeline `from Summary to action', Sum2Act for short. Empirical evaluations of our Sum2Act pipeline on the ToolBench benchmark show significant performance improvements, outperforming established methods like ReAct and DFSDT. This highlights Sum2Act's effectiveness in enhancing LLMs for complex real-world tasks.