CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents

Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, Xing Xie
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61092-61107, 2024.

Abstract

Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. Although most of the work has focused on cooperation and collaboration between agents, little work explores competition, another important mechanism that promotes the development of society and economy. In this paper, we seek to examine the competition dynamics in LLM-based agents. We first propose a general framework for studying the competition between agents. Then, we implement a practical competitive environment using GPT-4 to simulate a virtual town with two types of agents, including restaurant agents and customer agents. Specifically, the restaurant agents compete with each other to attract more customers, where competition encourages them to transform, such as cultivating new operating strategies. Simulation experiments reveal several interesting findings at the micro and macro levels, which align well with existing market and sociological theories. We hope that the framework and environment can be a promising testbed to study the competition that fosters understanding of society. Code is available at: https://github.com/microsoft/competeai.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-zhao24q, title = {{C}ompete{AI}: Understanding the Competition Dynamics of Large Language Model-based Agents}, author = {Zhao, Qinlin and Wang, Jindong and Zhang, Yixuan and Jin, Yiqiao and Zhu, Kaijie and Chen, Hao and Xie, Xing}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {61092--61107}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/zhao24q/zhao24q.pdf}, url = {https://proceedings.mlr.press/v235/zhao24q.html}, abstract = {Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. Although most of the work has focused on cooperation and collaboration between agents, little work explores competition, another important mechanism that promotes the development of society and economy. In this paper, we seek to examine the competition dynamics in LLM-based agents. We first propose a general framework for studying the competition between agents. Then, we implement a practical competitive environment using GPT-4 to simulate a virtual town with two types of agents, including restaurant agents and customer agents. Specifically, the restaurant agents compete with each other to attract more customers, where competition encourages them to transform, such as cultivating new operating strategies. Simulation experiments reveal several interesting findings at the micro and macro levels, which align well with existing market and sociological theories. We hope that the framework and environment can be a promising testbed to study the competition that fosters understanding of society. Code is available at: https://github.com/microsoft/competeai.} }
Endnote
%0 Conference Paper %T CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents %A Qinlin Zhao %A Jindong Wang %A Yixuan Zhang %A Yiqiao Jin %A Kaijie Zhu %A Hao Chen %A Xing Xie %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-zhao24q %I PMLR %P 61092--61107 %U https://proceedings.mlr.press/v235/zhao24q.html %V 235 %X Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. Although most of the work has focused on cooperation and collaboration between agents, little work explores competition, another important mechanism that promotes the development of society and economy. In this paper, we seek to examine the competition dynamics in LLM-based agents. We first propose a general framework for studying the competition between agents. Then, we implement a practical competitive environment using GPT-4 to simulate a virtual town with two types of agents, including restaurant agents and customer agents. Specifically, the restaurant agents compete with each other to attract more customers, where competition encourages them to transform, such as cultivating new operating strategies. Simulation experiments reveal several interesting findings at the micro and macro levels, which align well with existing market and sociological theories. We hope that the framework and environment can be a promising testbed to study the competition that fosters understanding of society. Code is available at: https://github.com/microsoft/competeai.
APA
Zhao, Q., Wang, J., Zhang, Y., Jin, Y., Zhu, K., Chen, H. & Xie, X.. (2024). CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:61092-61107 Available from https://proceedings.mlr.press/v235/zhao24q.html.

Related Material