aiqbench analysis
This paper critically examines the integration of Large Language Models into the agent-based modelling (ABM) workflow, analyzing their utility across the entire modelling cycle from problem formulation to result communication. It identifies specific opportunities where LLMs can enhance unstructured data processing and logical reasoning while highlighting inherent challenges for this specialized simulation community. The work provides a necessary technical assessment of how generative AI capabilities intersect with established computational social science methods.
Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle
arXiv:2507.05723v1 Announce Type: cross Abstract: 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.
Abstract: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.
Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Software Engineering (cs.SE)
arXiv:2507.05723 [cs.MA]
(or arXiv:2507.05723v1 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2507.05723 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 216 words
