LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation
Top Cited Papers
- 12 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
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 signifi cant 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 ef f iciency, 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.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2024YFE0203200)
- National Natural Science Foundation of China (U24A20329)
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM103)
- Science Fund for Creative Research Groups (62121002)
This publication has 44 references indexed in Scilit:
- Open e-commerce 1.0, five years of crowdsourced U.S. Amazon purchase histories with user demographicsScientific Data, 2024
- GPT detectors are biased against non-native English writersPatterns, 2023
- Discovering Emergent Agent Behaviour with Evolutionary Finite State Machines2018
- The Development and Validation of the Rational and Intuitive Decision Styles ScaleJournal of Personality Assessment, 2016
- Herd behavior in a complex adaptive systemProceedings of the National Academy of Sciences, 2011
- Adaptive memory: Survival processing enhances retention.Journal of Experimental Psychology: Learning, Memory, and Cognition, 2007
- Collective dynamics of ‘small-world’ networksNature, 1998
- The development of markers for the Big-Five factor structure.Psychological Assessment, 1992
- Human Memory: A Proposed System and its Control Processes1968
- The small-world problem1967