ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models

TL;DR

ModelScope-Agent is a flexible, open-source framework that enables the development of customizable AI agents using large language models, supporting tool integration, training, and real-world application deployment.

Contribution

It introduces a comprehensive, open-source agent framework that integrates multiple LLMs with external tools and APIs for practical, real-world AI applications.

Findings

Supports training on multiple open-source LLMs

Enables seamless integration with APIs and tools

Demonstrated with ModelScopeGPT, connecting 1000+ AI models

Abstract

Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further unleash the power of LLMs to accomplish complex tasks, there is a growing trend to build agent framework that equips LLMs, such as ChatGPT, with tool-use abilities to connect with massive external APIs. In this work, we introduce ModelScope-Agent, a general and customizable agent framework for real-world applications, based on open-source LLMs as controllers. It provides a user-friendly system library, with customizable engine design to support model training on multiple open-source LLMs, while also enabling seamless integration with both model APIs and common APIs in a unified way. To equip the LLMs with tool-use abilities, a comprehensive framework has been proposed spanning over tool-use data collection, tool retrieval, tool registration, memory control, customized model training, and evaluation for practical real-world applications. Finally, we showcase ModelScopeGPT, a real-world intelligent assistant of ModelScope Community based on the ModelScope-Agent framework, which is able to connect open-source LLMs with more than 1000 public AI models and localized community knowledge in ModelScope. The ModelScope-Agent library\footnote{https://github.com/modelscope/modelscope-agent} and online demo\footnote{https://modelscope.cn/studios/damo/ModelScopeGPT/summary} are now publicly available.