User Behavior Simulation with Large Language Model based Agents

TL;DR

This paper introduces an LLM-based agent framework and sandbox environment for simulating human user behaviors, achieving high realism and enabling studies of social phenomena like information cocoons and conformity.

Contribution

It presents a novel LLM-driven simulation paradigm and environment for realistic human behavior modeling and social phenomenon analysis.

Findings

Simulated behaviors closely match real human data

Effective in modeling information cocoons

Able to study user conformity behaviors

Abstract

Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences have suggested that by learning huge amounts of web knowledge, large language models (LLMs) can achieve human-like intelligence. We believe these models can provide significant opportunities to more believable user behavior simulation. To inspire such direction, we propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans. Concerning potential applications, we simulate and study two social phenomenons including (1) information cocoons and (2) user conformity behaviors. This research provides novel simulation paradigms for human-centered applications.