Human intelligence has the remarkable ability to assemble basic skills into complex ones so as to solve complex tasks. This ability is equally important for Artificial Intelligence (AI), and thus, we assert that in addition to the development of large, comprehensive intelligent models, it is equally crucial to equip such models with the capability to harness various domain-specific expert models for complex task-solving in the pursuit of Artificial General Intelligence (AGI). Recent developments in Large Language Models (LLMs) have demonstrated remarkable learning and reasoning abilities, making them promising as a controller to select, synthesize, and execute external models to solve complex tasks. In this project, we develop OpenAGI, an open-source AGI research platform, specifically designed to offer complex, multi-step tasks and accompanied by task-specific datasets, evaluation metrics, and a diverse range of extensible models. OpenAGI formulates complex tasks as natural language queries, serving as input to the LLM. The LLM subsequently selects, synthesizes, and executes models provided by OpenAGI to address the task. Furthermore, we propose a Reinforcement Learning from Task Feedback (RLTF) mechanism, which uses the task-solving result as feedback to improve the LLM's task-solving ability. Thus, the LLM is responsible for synthesizing various external models for solving complex tasks, while RLTF provides feedback to improve its task-solving ability, enabling a feedback loop for self-improving AI. We believe that the paradigm of LLMs operating various expert models for complex task-solving is a promising approach towards AGI. To facilitate the community's long-term improvement and evaluation of AGI's ability, we open-source the code, benchmark, and evaluation methods of the OpenAGI project at https://github.com/agiresearch/OpenAGI.

翻译：人类智能具有将基本技能组合成复杂技能以解决复杂任务的卓越能力。这一能力对于人工智能同样重要，因此我们认为，在开发大规模、综合性智能模型的同时，赋予此类模型利用各类特定领域专家模型解决复杂任务的能力，对于实现通用人工智能同样至关重要。近年来，大语言模型展现出显著的学习与推理能力，使其有望作为控制器来选择、整合并执行外部模型以解决复杂任务。在本项目中，我们开发了OpenAGI——一个开源的通用人工智能研究平台，专门设计用于提供复杂、多步骤的任务，并附带任务特定数据集、评估指标及多种可扩展模型。OpenAGI将复杂任务表述为自然语言查询，作为大语言模型的输入。大语言模型随后选择、整合并执行OpenAGI提供的模型以完成任务。此外，我们提出了一种基于任务反馈的强化学习机制，该机制利用任务解决结果作为反馈来提升大语言模型的任务解决能力。因此，大语言模型负责整合各类外部模型以解决复杂任务，而RLTF机制则提供反馈以提升其任务解决能力，从而形成自我改进型人工智能的反馈循环。我们相信，大语言模型操控多种专家模型以解决复杂任务的范式是实现通用人工智能的一条有前景的路径。为促进社区对通用人工智能能力的长期改进与评估，我们在https://github.com/agiresearch/OpenAGI开源了OpenAGI项目的代码、基准测试及评估方法。