War and Peace (WarAgent): LLM-based Multi-Agent Simulation of World Wars
Keywords: large language model, multi-agent system, social simulation
TL;DR: This research explores the potential of Artificial Intelligence and Large Language Models in understanding and simulating complex human behaviors, specifically in the context of historical international conflicts
Abstract: This research explores the potential of Artificial Intelligence and Large Language Models in understanding and simulating complex human behaviors, specifically in the context of historical international conflicts. We introduce WarAgent, an LLM-powered multi-agent AI system, to simulate the decisions and consequences of participating countries in three specific historical conflicts. In addition, we propose standard evaluation protocols for LLM-based Multi-agent Systems simulation. Our study provides a nuanced analysis of the strengths and limitations of current MAS systems in simulating complex collective human behaviors under diverse settings of international conflicts. The emergent interactions among agents in our simulations offer fresh perspectives on the triggers and conditions leading to war. Our findings offer data-driven and AI-augmented insights that can help redefine how we approach conflict resolution and peacekeeping strategies. While we acknowledge the potential of AI in providing data-driven insights, we caution against over-reliance and emphasize the need for careful interpretation in conflict resolution and peacekeeping strategies. The implications of this work extend beyond computer simulation, offering a potential avenue for using AI to better understand human history. Code and data are available at \url{https://anonymous.4open.science/r/WarAgent-0FF0}
Primary Area: other topics in machine learning (i.e., none of the above)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 3412
Loading