Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning

TL;DR

Reverse Chain introduces a rule-based, controllable method enabling LLMs to effectively perform multi-API planning and execution through prompts, improving their ability to handle complex, multi-step external API interactions without fine-tuning.

Contribution

It proposes a novel backward reasoning rule for LLMs to manage multi-API calls via prompts, a significant step towards more capable tool-use in LLMs without additional training.

Findings

Reverse Chain achieves high accuracy in multi-API task management.

The approach outperforms baseline methods in API selection and argument completion.

Extensive experiments demonstrate its effectiveness in multi-API scenarios.

Abstract

While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting without fine-tuning. This paper introduces ``Reverse Chain'', a controllable, target-driven approach designed to empower LLMs with the capability to operate external APIs only via prompts. Recognizing that most LLMs have limited tool-use capabilities, Reverse Chain limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion. Furthermore, to manage a controllable multi-function calling, Reverse Chain adopts a generic rule based on a backward reasoning process. This rule determines when to do API selection or Argument completion. To evaluate the multi-tool-use capability of LLMs, we have released a compositional multi-tool task dataset, available at \url{https://anonymous.4open.science/r/reverse-chain-8681}. Extensive numerical experiments validate the remarkable proficiency of Reverse Chain in managing multiple API calls.