This paper introduces a novel human-LLM interaction framework, Low-code LLM, that incorporates six types of low-code visual programming interactions to achieve more controllable and stable responses. The proposed framework consists of a Planning LLM that designs a structured planning workflow for complex tasks and an Executing LLM that generates responses following the user-confirmed workflow. The low-code LLM offers controllable generation results, user-friendly interaction, and broadly applicable scenarios. The system is demonstrated using four typical applications, and it aims to bridge the gap between humans and LLMs to enable more effective and efficient utilization of LLMs for complex tasks.
