[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83133-en":3,"doc-seo-83133-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83133,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","LLM-powered reasoning in agent-based modeling","Agent-based modeling (ABM) can represent millions of individuals and interactions, enabling population-scale digital twins for policy decisions, but it often depends on static, outdated data and cannot adapt to real-time changes in human behavior during dynamic scenarios. This work introduces the HALE (Hybrid Agent-based and Language-driven Epidemic) framework that uses large language models to predict decision-making as an epidemic unfolds. A COVID-19 simulation for Salt Lake County, UT (Sep 2020–Feb 2022) captures the observed epidemic peak and size better than ABM-only approaches.","arXiv :2607 .06757v 1 [ cs .AI ] 7 Jul 2026  \nLLM-powered reasoning in agent-based modeling  \nSifat Afroj Moon∗, Dakotah Maguire 1 , Adam Spannaus 1 , Joe Tuccillo2 , Maksudul Alam3 , Sudip K. Seal3 , John Gounley 1 and Heidi Hanson 1  \n1 Computational Science and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA  \n2 Geospatial Science and Human Security Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA  \n3 Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA  \nAbstract  \nAgent-based modeling (ABM) has the capability to model millions of individual humans and their interactions, which is valuable for constructing a population-scale digital twin to support policy decisions. However, ABMs have traditionally relied on static and outdated data, which prevents the models from adapting to real-time changes in a given scenario. Complete realtime information about the activities of a population is often dynamic, as mobility depends on epidemic conditions and human decision-making. The research presented here provides a novel approach to addressing this information gap. Large language models (LLMs) offer new opportunities to predict human decision-making as a scenario unfolds. To this end, we introduce a scalable Hybrid Agent-based and Language-driven Epidemic (HALE) modeling framework that leverages LLMs to predict human decision-making in an ABM simulation. As a proof-of-concept, we use HALE to simulate COVID-19 and its effects in Salt Lake County, UT, from September 2020 to February 2022 . The HALE framework better captures the observed epidemic peak and size, whereas simulations that use only ABM tend to overestimate the epidemic’s effects.  \nKeywords: Large language models (LLMs), agent-based modeling (ABM), activity-based network, individual-based network model, digital twin, COVID-19 .  \n1 Introduction  \nAgent-based modeling (ABM) is a powerful tool for modeling complex dynamic systems at the individual level. Understanding the impact of individual behavior on disease spread is critical for accurate disease forecasts. ABM enables us to model individual human behavior (e.g., maskwearing, vaccine acceptance) based on a distribution of a population, their movement over time, and their social interactions [2] . Typically, ABMs are initialized with these parameters, and the complex interactions of agents are modeled over a set time period. However, human behavior is inherently uncertain and depends on various factors, including social environment, geographic location, climate, and weather. Human preferences also change over time based on external environments and social pressures. The reasoning abilities of large language models (LLMs) can assist in modeling change in human behavior during a disease outbreak [7, 39, 33, 15] .  \n∗ Corresponding [author: moons@ornl.gov](author: moons@ornl.gov)  \nAlthough advancements in LLMs have improved knowledge across various domains [40], their application in epidemic modeling—especially individual-based network modeling—has not yet been fully explored.  \nLLMs can assist epidemic modeling and simulation in various ways, such as performing literature reviews, forecasting epidemics [16], and predicting human reactions to an epidemic [7] . LLM agents can also exhibit realistic human behaviors [13] . Interestingly, the collective intelligence of a generative agent-based model can mimic real-world responses to disease spreading [36] . In this study, we investigate how LLMs can infer the change in human behavior during an epidemic and support ABMs in dynamically updating network structures. These ABM-based population-scale digital twins use real-world human activity data, which consist of different types of activities, including staying at home, going to school, being in the office, and shopping, along with their respective locations. However, detailed activity data are often difficult to obtain, and this difficult","cbCaijlKpPwq93TO","https://ap.wps.com/l/cbCaijlKpPwq93TO","pdf",1705058,1,17,"English","en",105,"# Introduction\n## Motivation and challenges in ABM for epidemic modeling\n## How LLMs support dynamic behavior and network updates\n## Activity-based temporal network modeling","[{\"question\":\"What problem does HALE address in traditional ABM epidemic modeling?\",\"answer\":\"Traditional ABMs rely on static and outdated data, so they cannot adapt to real-time changes in human decisions. HALE targets this information gap by predicting decision-making as conditions evolve.\"},{\"question\":\"How does HALE use large language models within an agent-based simulation?\",\"answer\":\"HALE leverages LLMs to infer human decision-making during an ABM simulation. It updates behavior and network-related dynamics rather than keeping them fixed.\"},{\"question\":\"What case study is used to validate HALE?\",\"answer\":\"The proof-of-concept simulates COVID-19 effects in Salt Lake County, UT, from September 2020 to February 2022. HALE better matches the observed epidemic peak and overall size than ABM-only simulations.\"}]",1784185518,43,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"llm-powered-reasoning-in-agent-based-modeling","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/llm-powered-reasoning-in-agent-based-modeling/83133/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does HALE address in traditional ABM epidemic modeling?","Question",{"text":75,"@type":76},"Traditional ABMs rely on static and outdated data, so they cannot adapt to real-time changes in human decisions. HALE targets this information gap by predicting decision-making as conditions evolve.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does HALE use large language models within an agent-based simulation?",{"text":80,"@type":76},"HALE leverages LLMs to infer human decision-making during an ABM simulation. It updates behavior and network-related dynamics rather than keeping them fixed.",{"name":82,"@type":73,"acceptedAnswer":83},"What case study is used to validate HALE?",{"text":84,"@type":76},"The proof-of-concept simulates COVID-19 effects in Salt Lake County, UT, from September 2020 to February 2022. HALE better matches the observed epidemic peak and overall size than ABM-only simulations.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]