[论文解读] Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective

Qun Ma, Xue Xiao+10 more|arXiv (Cornell University)|Feb 1, 2024

Natural Language Processing Techniques被引用 8

一句话总结

本文综述将基于大型语言模型（LLM）的代理整合到计算实验和基于代理的建模中，讨论其利弊，并概述未来方向。

ABSTRACT

Computational experiments have emerged as a valuable method for studying complex systems, involving the algorithmization of counterfactuals. However, accurately representing real social systems in Agent-based Modeling (ABM) is challenging due to the diverse and intricate characteristics of humans, including bounded rationality and heterogeneity. To address this limitation, the integration of Large Language Models (LLMs) has been proposed, enabling agents to possess anthropomorphic abilities such as complex reasoning and autonomous learning. These agents, known as LLM-based Agent, offer the potential to enhance the anthropomorphism lacking in ABM. Nonetheless, the absence of explicit explainability in LLMs significantly hinders their application in the social sciences. Conversely, computational experiments excel in providing causal analysis of individual behaviors and complex phenomena. Thus, combining computational experiments with LLM-based Agent holds substantial research potential. This paper aims to present a comprehensive exploration of this fusion. Primarily, it outlines the historical development of agent structures and their evolution into artificial societies, emphasizing their importance in computational experiments. Then it elucidates the advantages that computational experiments and LLM-based Agents offer each other, considering the perspectives of LLM-based Agent for computational experiments and vice versa. Finally, this paper addresses the challenges and future trends in this research domain, offering guidance for subsequent related studies.

研究动机与目标

• 解释计算实验与ABM如何发展为人工社会。
• 突出基于LLM的代理的拟人能力及其提升ABM的潜力。
• 分析计算实验与基于LLM的代理之间的互利性与互补性。
• 识别挑战，特别是可解释性，并提出未来的研究方向。

提出的方法

• 回顾代理结构的历史发展及其向人工社会的演进。
• 从双重视角综合计算实验与基于LLM的代理的优势（面向实验的LLM代理以及面向LLM代理的实验）。
• 讨论在社会科学应用中的可解释性与信任等挑战。
• 为进入这一跨学科领域的研究者提供指导和未来研究趋势。

实验结果

研究问题

• RQ1 在计算实验中，代理结构和人工社会的历史趋势是什么？
• RQ2 将基于LLM的代理与计算实验/ABM结合的互利性与局限性是什么？
• RQ3 在将基于LLM的代理应用于社会科学研究时，尤其是在可解释性方面，会出现哪些挑战？
• RQ4 在这一领域交叉研究中，哪些未来方向与建议最能引导后续研究？

主要发现

• 基于LLM的代理可以为ABM增加拟人化推理和自主学习。
• 计算实验提供因果分析能力，可补充基于LLM的代理。
• 存在整合机会，利用各自领域的优势来研究复杂社会现象。
• 可解释性仍是阻碍在社会科学领域广泛采用的核心难题。