arXiv 2507.057232025-07cs.MAcs.AIcs.CYcs.SE

大型语言模型在基于智能体建模中的应用：建模周期中的当前及潜在用途

Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle

Umeå Universitet（于默奥大学）；UiT The Arctic University of Norway（挪威北极大学）；University of Nottingham（诺丁汉大学）；University of Leeds（利兹大学）；Norwegian University of Science and Technology（挪威科技大学）；NORCE Norwegian Research Center AS（挪威研究中心有限公司）；University of West Bohemia（西波希米亚大学）；Bar Ilan University（巴伊兰大学）；University of Southern Denmark（南丹麦大学）；University College Dublin（都柏林大学学院）；University of Warwick（华威大学）

Loïs Vanhée, Melania Borit, Peer-Olaf Siebers, Roger Cremades, Christopher Frantz, Önder Gürcan, František Kalvas, Denisa Reshef Kera, Vivek Nallur, Kavin Naras… 展开作者

Loïs Vanhée, Melania Borit, Peer-Olaf Siebers, Roger Cremades, Christopher Frantz, Önder Gürcan, František Kalvas, Denisa Reshef Kera, Vivek Nallur, Kavin Narasimhan, Martin Neumann

备注：: 18 pages, including 2 pages of appendix, accepted for publication at the Social Simulation Conference 2025 (https://ssc2025.tbm.tudelft.nl/)
发表信息：: Verhagen, H., Chappin, E., Scholz, G. (eds) Advances in Social Simulation. SSC 2025. Springer Proceedings in Complexity. Springer, Cham
DOI：: 10.1007/978-3-032-31712-4_43

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文回顾大型语言模型（LLMs）在基于智能体建模（ABM）中的当前应用，结合建模周期从问题构建到结果传播的全流程，批判性反思其潜在应用的机遇与挑战，探索LLMs对ABM建模过程的赋能价值。

摘要：

具有日益复杂的自然语言理解和生成能力的大型语言模型（LLMs）的出现，引发了基于智能体建模（ABM）社区的兴趣。LLMs具备文本总结、生成、分析、分类、转录、翻译、问答、解释提出、对话维持、非结构化文本信息提取以及逻辑推理和问题解决能力，在建模过程中具有良好的应用潜力。本文回顾了LLMs在ABM中的当前应用后，遵循从问题构建到模型结果文档化与传播的建模周期，以批判性视角反思了LLMs在ABM中潜在应用的机遇与挑战。

英文摘要：

The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked interest in the Agent-based Modelling (ABM) community. With their ability to summarize, generate, analyze, categorize, transcribe and translate text, answer questions, propose explanations, sustain dialogue, extract information from unstructured text, and perform logical reasoning and problem-solving tasks, LLMs have a good potential to contribute to the modelling process. After reviewing the current use of LLMs in ABM, this study reflects on the opportunities and challenges of the potential use of LLMs in ABM. It does so by following the modelling cycle, from problem formulation to documentation and communication of model results, and holding a critical stance.

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。