CHI2025_Plan-then-Execute_LLMAgent

This repo contains all code, data, and user interfaces associated with paper "Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant." In our study, we analyzed different extents of user involvement in the planning and execution stages of LLM agents. Our data is evaluated based on action sequences. We also recorded how users interact with LLM agents and provided an interface built upon Flask.