AI 中文总结
本研究通过公共品博弈实验，考察了四种大型语言模型在动态网络中的合作行为，发现模型架构、网络拓扑和提示设计显著影响合作率，为基于LLM的社会模拟提供了初步框架。
AI 中文摘要
合作是人类社会的基石，使得在动态和不确定的环境中实现集体进步成为可能。随着自主行动的AI系统的出现，理解人机合作以及自适应网络中AI与AI之间的交互变得至关重要。在本工作中，我们研究了使用大型语言模型——Mistral、Llama3、Gemma3和Phi3——的AI在动态网络结构中的公共品博弈中的交互。我们的实验在单模型和混合模型条件下，跨越Watts-Strogatz（WS）、Barabasi-Albert（BA）和Erdos-Renyi（ER）网络进行。我们分析了模型架构、网络拓扑和提示设计对合作行为的影响。结果表明，Mistral和Llama3提供高合作率，而Phi3表现出背叛倾向。此外，Erdos-Renyi网络的随机结构显著提高了合作水平。提示设计也起着关键作用；一个社会利益提示导致更高的合作水平。这些发现为基于LLM的自适应社交网络模拟提供了一个初步框架。
英文摘要
Cooperation is a cornerstone of human societies, enabling collective progress in dynamic and uncertain environments. With the advent of AI systems acting autonomously, it becomes crucial to understand not only human-AI cooperation but also AI-AI interactions in adaptive networks. In this work, we examine the interactions of AI using Large Language Models -- Mistral, Llama3, Gemma3, and Phi3 -- in a public goods game within dynamic network structures. Our experiments were conducted under single-model and mixed-model conditions across Watts-Strogatz (WS), Barabasi-Albert (BA), and Erdos-Renyi (ER) networks. We analyzed the impact of model architecture, network topology, and prompt design on cooperative behavior. Results show that Mistral and Llama3 offer high cooperation rates, while Phi3 shows defective tendencies. Additionally, the random structure of Erdos-Renyi networks dramatically improves cooperation. Prompt design also plays a key role; a society-benefits prompt leads to a higher cooperation level. These findings offer a preliminary framework for LLM-based simulations in adaptive social networks.
Comments7 pages, 5 figures, 2 tables. Accepted at LLAIS 2025: Workshop on Large Language Model Agents for Intelligent Systems, Bologna, Italy
