[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82976-en":3,"doc-seo-82976-105":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},82976,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Agents with Feelings: Personality and Emotion in Multi-Agent Software Teams","Multi-agent LLM systems for software engineering usually distinguish agents by roles and workflows, yet the effect of agents’ behavioral profiles on team outcomes is unclear. This study examines how personality and emotion profiles shape LLM agent teams via a psychology-informed framework combining Big Five traits, basic emotions, SE-relevant work styles, and task roles. Across 78 configurations over 659 code-generation and code-review instances using four LLMs, profile choice significantly affects performance, collaboration dynamics, and cost.","Agents with Feelings? Personality and Emotion in  \nMulti-Agent Software Teams  \n1st Yunyan Ding Department of Computer Science University of California, Irvine Irvine, United States [yunyad1@uci.edu](yunyad1@uci.edu)  \n2nd Thomas Zimmermann Department of Informatics University of California, Irvine Irvine, United States [tzimmer@uci.edu](tzimmer@uci.edu)  \n3rd Iftekhar Ahmed Department of Informatics University of California, Irvine Irvine, United States [iftekha@uci.edu](iftekha@uci.edu)  \narXiv :2607 .05659v 1 [ cs . SE] 6 Jul 2026  \nAbstract—Multi-agent LLM systems for Software Engineering (SE) typically differentiate agents through roles and workflows, but little is known about how agents’ behavioral profiles affect team performance. We investigate the impact of personality and emotion profiles on LLM agent teams using a psychologyinformed framework that combines Big Five personality traits, basic emotions, SE-relevant work styles, and task roles. We evaluate 78 team-profile configurations across code generation and code review using four LLMs and 659 task instances. Results show that profile choice substantially affects both performance and team behavior. For code generation, the gap between the best and worst shared-profile configurations reaches 7.1–11.3 percentage points in pass@1 across models, while the best mixedprofile configuration outperforms the best shared-profile configuration in six of eight model–task settings. Profiles also influence collaboration dynamics and cost: fear and high-conscientiousness profiles increase revision activity, over-revision, and token usage without consistent performance gains. These findings identify agent profiles as an important design dimension in multi-agent SE systems, affecting not only task outcomes but also the efficiency of collaboration.  \nIndex Terms—large language models, multi-agent systems, code generation, code review, personality, emotion  \nI. INTRODUCTION  \nLarge Language Models (LLMs) are increasingly used to support a wide range of Software Engineering (SE) tasks [1],[2] . To address the collaborative nature of software development, recent SE-oriented multi-agent systems, such as ChatDev and MetaGPT [3], [4], organize LLM agents around software development workflows and assign them roles that mirror those in software teams. These systems primarily differentiate agents by their responsibilities, defining what each agent does. However, in human software teams, individuals differ not only in the work they perform but also in how they approach it, due to characteristics such as personality, emotional state, and work style. Psychology research has shown that personality traits are associated with individual job performance [5], [6] . At the team level, personality composition influences team effectiveness and performance [7], [8] . SE research similarly suggests that personality and personality diversity affect team outcomes [9]–[11] . Beyond relatively stable personality traits, transient emotional states also influence behavior, decisionmaking, and performance [12] . These findings raise the ques-  \ntion of whether personality and emotion profiles similarly shape the behavior and performance of LLM-agent teams.  \nPrior research has shown that persona-based prompts can influence LLM behavior [13],[14] and can steer LLM outputs toward specific roles or human subpopulations [15] . Similarly, emotion-oriented prompting studies indicate that emotional cues can influence LLM behavior and performance [16] . In SE, persona-guided prompting has been shown to improve code generation in single-agent settings [17] . Beyond SE, studies of multi-agent LLM systems have found that assigning agents different personality traits, such as Big Five-based traits, can influence team performance [18] . However, while prior work has examined personality-and emotion-based prompting in individual LLMs and non-SE multi-agent settings, their impact on collaborative SE teams remains largely unexp","cbCainmLsAk4OdCT","https://ap.wps.com/l/cbCainmLsAk4OdCT","pdf",2260719,4,1,12,"English","en",105,"# Introduction\n## Related Work\n## Research Gap and Approach","[{\"question\":\"How does the paper define an agents’ personality and emotion profile in LLM teams?\",\"answer\":\"It defines a profile as a personality and emotion configuration assigned to an agent, and a persona description as the natural-language text reflecting that profile together with the agent’s SE task role and work-style tendencies.\"},{\"question\":\"Which two types of profile settings are evaluated?\",\"answer\":\"The study evaluates shared-profile teams, where all agents use the same profile, and mixed-profile teams, where agents are assigned different profiles.\"},{\"question\":\"What impact do personality and emotion profiles have on team performance and collaboration cost?\",\"answer\":\"Profile choice substantially changes both performance and team behavior. Fear and high-conscientiousness profiles increase revision activity, over-revision, and token usage without consistent performance gains.\"}]",1784184413,30,{"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},"agents-with-feelings-personality-and-emotion-in-multi-agent-software-teams","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/agents-with-feelings-personality-and-emotion-in-multi-agent-software-teams/82976/",{"url":52,"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","2026-07-24","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},"How does the paper define an agents’ personality and emotion profile in LLM teams?","Question",{"text":75,"@type":76},"It defines a profile as a personality and emotion configuration assigned to an agent, and a persona description as the natural-language text reflecting that profile together with the agent’s SE task role and work-style tendencies.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which two types of profile settings are evaluated?",{"text":80,"@type":76},"The study evaluates shared-profile teams, where all agents use the same profile, and mixed-profile teams, where agents are assigned different profiles.",{"name":82,"@type":73,"acceptedAnswer":83},"What impact do personality and emotion profiles have on team performance and collaboration cost?",{"text":84,"@type":76},"Profile choice substantially changes both performance and team behavior. Fear and high-conscientiousness profiles increase revision activity, over-revision, and token usage without consistent performance gains.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]