[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82688-en":3,"doc-seo-82688-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82688,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Evaluating Large Language Models for Decision-Making in Agent-Based Urban Mobility Simulations","Urban mobility modeling faces the challenge of representing decision-making in dynamic environments where adaptive behavior matters. This work integrates Large Language Models (LLMs) into agent-based simulations by proposing a hybrid architecture connecting the GAMA platform to an external LLM module via an API. Agents use the LLM as a decision layer to determine whether route replanning is needed, while persistent memory shapes future choices. Comparisons across road-blockage scenarios and population scales assess rule-based versus LLM-assisted approaches.","arXiv :2607 .027 16v 1 [ cs .MA] 2 Jul 2026  \nEvaluating Large Language Models for Decision-Making in Agent-Based Urban Mobility  \nSimulations  \nBruno Cascaes Alves 1 , Míriam Blank Born 1 , Ulisses Gilioli Francescatto Júnior2 , Felipe Moura Goulart3 , Letícia Brandão Caldas3 , and Marilton Sanchotene de Aguiar 1  \n1 Postgraduate Program in Computing  \n2 Undergraduate in Computer Science  \n3 Undergraduate in Computer Engineering  \nFederal University of Pelotas, Pelotas, Brazil {bcalves,mbborn,ugfjunior,fmgoulart,lbcaldas,[marilton}@inf.ufpel.edu.br](marilton}@inf.ufpel.edu.br)  \nAbstract. Urban mobility modeling faces challenges in representing decision-making in dynamic environments. Although Multi-Agent Systems are widely used, rule-based approaches rely on fixed heuristics that limit adaptive behavior. This work investigates the integration of Large Language Models (LLMs) as decision-making components in multi-agent simulations. We propose a hybrid architecture that connects the GAMA platform to an external LLM-based module through an API, enabling agents to determine whether route replanning is necessary. Rather than replacing routing algorithms, the LLM serves as a decision layer that guides replanning behavior. The approach incorporates persistent memory, allowing past interactions to influence future decisions and promote behavioral consistency. We compare rule-based and LLM-assisted approaches across multiple road-blockage scenarios and population scales.  \nResults indicate that LLM-enabled agents exhibit greater adaptability and contextual awareness, particularly in scenarios with higher route flexibility. Memory influences performance and behavioral consistency, with effects varying across configurations. Overall, LLMs serve as complementary cognitive layers that enrich behavioral representations in urban mobility simulations and hold potential for modeling complex decisionmaking in spatial multi-agent systems.  \nKeywords: Agent-Based Modeling · GAMA Platform · Large Language Models · Multi-Agent Systems · Urban Mobility.  \n1 Introduction  \nUrban mobility management faces the challenge of predicting and mitigating the impacts of events in increasingly saturated transportation networks [8] . The efficacy of interventions depends on the understanding that traffic dynamics emerge from individual behavioral decisions made by agents in dynamic environments  \n2 B. C. Alves et al.  \nunder uncertainty [4] . In this context, Artificial Intelligence (AI) emerges as a component for increasing realism of experiments, enabling the incorporation of adaptation and contextual reasoning in urban mobility analysis [12] .  \nMulti-Agent Systems (MAS) simulations have consolidated as a predominant approach for representing individuals and analyzing their impacts on urban systems. This approach enables the investigation of mobility dynamics through the interaction of autonomous agents in dynamic environments, capable of making decisions to achieve individual or collective goals [17] . However, traditional modeling often relies on fixed heuristics and predefined rules, limiting behavioral adaptability in high-contextual-variability scenarios.  \nTo mitigate these limitations, Large Language Models (LLMs) emerge asa promising alternative for enriching decision-making in agent-based systems. Models such as GPT [1] and Gemini [2] exhibit reasoning and semantic capabilities that enable the processing of contextual information [10] . By integrating these models into MAS, agents can exhibit greater behavioral flexibility and make more context-sensitive decisions aligned with environmental conditions.  \nRecent studies demonstrate advances in LLM-based Agentic frameworks, in which these models serve as system cores capable of planning and iterating on their own actions. These frameworks, including Agno [13] and CrewAI [16], utilize memory mechanisms and integration with external tools, promoting greater consistency and continuity in decision-makin","cbCaif8ft62nbJqg","https://ap.wps.com/l/cbCaif8ft62nbJqg","pdf",1150438,2,1,15,"English","en",105,"# Introduction\n# Theoretical Background","[{\"question\":\"Why do traditional rule-based agent approaches limit urban mobility simulation realism?\",\"answer\":\"Rule-based approaches rely on fixed heuristics and predefined rules, which restrict behavioral adaptability under high contextual variability in dynamic environments.\"},{\"question\":\"How are Large Language Models integrated into the GAMA-based simulations?\",\"answer\":\"The method connects the GAMA platform to an external LLM-based decision module through an API, where the LLM determines whether agents should maintain their trajectory or trigger route replanning.\"},{\"question\":\"What role does persistent memory play in agent decision-making?\",\"answer\":\"Persistent memory allows past interactions to influence future decisions, supporting behavioral consistency; its effects vary across configurations and performance outcomes.\"}]",1784182297,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"evaluating-large-language-models-for-decision-making-in-agent-based-urban-mobility-simulations","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/evaluating-large-language-models-for-decision-making-in-agent-based-urban-mobility-simulations/82688/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","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},"Why do traditional rule-based agent approaches limit urban mobility simulation realism?","Question",{"text":75,"@type":76},"Rule-based approaches rely on fixed heuristics and predefined rules, which restrict behavioral adaptability under high contextual variability in dynamic environments.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are Large Language Models integrated into the GAMA-based simulations?",{"text":80,"@type":76},"The method connects the GAMA platform to an external LLM-based decision module through an API, where the LLM determines whether agents should maintain their trajectory or trigger route replanning.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does persistent memory play in agent decision-making?",{"text":84,"@type":76},"Persistent memory allows past interactions to influence future decisions, supporting behavioral consistency; its effects vary across configurations and performance outcomes.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]