LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation

TL;DR

LMAgent is a large-scale, multimodal multi-agent system based on LLMs that simulates complex social behaviors in e-commerce scenarios, demonstrating high realism and efficiency in multi-user interactions.

Contribution

The paper introduces LMAgent, a novel multimodal multi-agent system with self-consistency prompting and a fast memory mechanism, enabling large-scale, realistic social behavior simulation.

Findings

Agents achieve human-like behavioral indicators.

System supports over 10,000 agents efficiently.

Exhibits complex phenomena like herd behavior.

Abstract

The believable simulation of multi-user behavior is crucial for understanding complex social systems. Recently, large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-like intelligence across various tasks. However, real human societies are often dynamic and complex, involving numerous individuals engaging in multimodal interactions. In this paper, taking e-commerce scenarios as an example, we present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs. In LMAgent, besides freely chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce. To simulate this complex system, we introduce a self-consistency prompting mechanism to augment agents' multimodal capabilities, resulting in significantly improved decision-making performance over the existing multi-agent system. Moreover, we propose a fast memory mechanism combined with the small-world model to enhance system efficiency, which supports more than 10,000 agent simulations in a society. Experiments on agents' behavior show that these agents achieve comparable performance to humans in behavioral indicators. Furthermore, compared with the existing LLMs-based multi-agent system, more different and valuable phenomena are exhibited, such as herd behavior, which demonstrates the potential of LMAgent in credible large-scale social behavior simulations.