AutoAgents is an open-source, LLM-based experimental application for generating automated intelligent agents. Driven by LLMs, it can automatically generate multi-role intelligent agents based on your defined objectives. It can determine the required expert roles and specific execution plans based on the problem. Includes intelligent agent generator, execution plan generator, and result reflection module. Enables LLMs to autonomously allocate different roles based on problems, formulate solutions plans, and execute them, much like humans.