Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning
This addresses the problem of limited tool-use capabilities in LLMs for developers and researchers, offering a controllable method for multi-function calling, though it appears incremental as it builds on existing function-calling frameworks.
The paper tackles the challenge of enabling large language models to perform multi-API planning without fine-tuning by introducing Reverse Chain, a target-driven approach that uses a backward reasoning rule to manage API selection and argument completion, resulting in validated proficiency in handling multiple API calls.
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.