What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents (2402.13184v4)
Abstract: In this study, we introduce "CosmoAgent," an innovative artificial intelligence framework utilizing LLMs to simulate complex interactions between human and extraterrestrial civilizations, with a special emphasis on Stephen Hawking's cautionary advice about not sending radio signals haphazardly into the universe. The goal is to assess the feasibility of peaceful coexistence while considering potential risks that could threaten well-intentioned civilizations. Employing mathematical models and state transition matrices, our approach quantitatively evaluates the development trajectories of civilizations, offering insights into future decision-making at critical points of growth and saturation. Furthermore, the paper acknowledges the vast diversity in potential living conditions across the universe, which could foster unique cosmologies, ethical codes, and worldviews among various civilizations. Recognizing the Earth-centric bias inherent in current LLM designs, we propose the novel concept of using LLMs with diverse ethical paradigms and simulating interactions between entities with distinct moral principles. This innovative research provides a new way to understand complex inter-civilizational dynamics, expanding our perspective while pioneering novel strategies for conflict resolution, which are crucial for preventing interstellar conflicts. We have also released the code and datasets to enable further academic investigation into this interesting area of research. The code is available at https://github.com/MingyuJ666/Simulating-Alien-Civilizations-with-LLM-based-Agents.
- Science in the age of large language models. Nature Reviews Physics, April 2023.
- Language models are few-shot learners, 2020.
- Chateval: Towards better llm-based evaluators through multi-agent debate, 2023.
- Put your money where your mouth is: Evaluating strategic planning and execution of llm agents in an auction arena. arXiv preprint arXiv:2310.05746, 2023.
- Agent-based modeling of ancient societies and their organization structure. Autonomous Agents and Multi-Agent Systems, 30(6):1072–1116, nov 2016.
- Improving factuality and reasoning in language models through multiagent debate, 2023.
- Generative agent-based modeling: an introduction and tutorial. System Dynamics Review, January 2024.
- War and peace (waragent): Large language model-based multi-agent simulation of world wars, 2024.
- The impact of reasoning step length on large language models, 2024.
- Lyfe agents: Generative agents for low-cost real-time social interactions, 2023.
- Large language models are zero-shot reasoners, 2023.
- Camel: Communicative agents for "mind" exploration of large language model society, 2023.
- Modeling the warring states period: History dynamics of initial unified empire in china (475 bc to 221 bc). Expert Systems with Applications, 230:120560, 2023.
- Systematic review of agent-based and system dynamics models for social-ecological system case studies. Systems, 11(11), 2023.
- Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22, 2023.
- Introductory chapter: Multi-agent systems. In Jorge Rocha, editor, Multi-agent Systems, chapter 1. IntechOpen, Rijeka, 2017.
- Artificial intelligence a modern approach. London, 2010.
- Multi-agent collaboration: Harnessing the power of intelligent llm agents, 2023.
- Agent-based modelling of interstellar contacts using rumour spread models. International Journal of Astrobiology, 19(6):423–429, 2020.
- Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
- Intelligent agents: Theory and practice. The knowledge engineering review, 10(2):115–152, 1995.
- The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023.