模拟人类策略行为:比较单智能体与多智能体大语言模型
Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
AI总结:
本文比较单智能体与多智能体大语言模型在最后通牒博弈中模拟人类策略推理的能力,发现多智能体系统在模拟贪婪与公平性格组合时准确率达88%,显著优于单智能体的50%,表明LLMs可用于辅助政策和决策的初步探索。
摘要:
在为人们制定政策、计划或设计方案时,设计者很难预见人们可能进行推理和采取行为的所有方式。近年来,大语言模型(LLMs)已被证明能够模拟人类推理。我们通过测量LLMs在最后通牒博弈这一经典经济学议价实验中模拟策略推理的能力来扩展这一工作。实验证据表明,人类的策略推理是复杂的;人们往往会选择惩罚其他参与者以维护社会规范,即使这需要付出个人代价。我们测试LLMs能否在模拟中复现这种行为,并比较两种结构:单智能体LLMs和多智能体系统。我们比较了它们在以下方面的能力:(1)在最后通牒博弈中模拟类人推理,(2)模拟两种参与者性格——贪婪和公平,以及(3)创建逻辑完整且与性格一致的稳健策略。我们的评估表明,在模拟性格组合的人类推理和行为方面,多智能体系统比单智能体LLMs更准确(88%对50%)。因此,利用LLMs模拟人类策略推理,以帮助决策者和政策制定者对人在系统中的行为方式进行初步探索,是具有潜力的。
英文摘要:
When creating policies, plans, or designs for people, it is challenging for designers to foresee all of the ways in which people may reason and behave. Recently, Large Language Models (LLMs) have been shown to be able to simulate human reasoning. We extend this work by measuring LLMs ability to simulate strategic reasoning in the ultimatum game, a classic economics bargaining experiment. Experimental evidence shows human strategic reasoning is complex; people will often choose to punish other players to enforce social norms even at personal expense. We test if LLMs can replicate this behavior in simulation, comparing two structures: single LLMs and multi-agent systems. We compare their abilities to (1) simulate human-like reasoning in the ultimatum game, (2) simulate two player personalities, greedy and fair, and (3) create robust strategies that are logically complete and consistent with personality. Our evaluation shows that multi-agent systems are more accurate than single LLMs (88 percent vs. 50 percent) in simulating human reasoning and actions for personality pairs. Thus, there is potential to use LLMs to simulate human strategic reasoning to help decision and policy-makers perform preliminary explorations of how people behave in systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。