[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-293093-105":59,"doc-detail-293093-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","psychologically-enhanced-ai-agents","Psychologically Enhanced AI Agents","","We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Using the Myers–Briggs Type Indicator (MBTI), the method primes agents with distinct personality archetypes via prompt engineering, controlling behavior across cognition and affect. Experiments show consistent, interpretable behavioral biases: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt stable strategies in game-theoretic tasks. The framework supports structured multi-agent protocols and improves cooperation by enabling self-reflection before interaction. Trait persistence is verified using the official 16Personalities test, and the approach generalizes to other psychological models such as Big Five, HEXACO, and Enneagram, without fine-tuning.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/psychologically-enhanced-ai-agents/293093/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/psychologically-enhanced-ai-agents/293093.png","ImageObject",300,407,{"name":92,"@type":93},"Riley West","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is MBTI-in-Thoughts, and what does it enhance in LLM agents?","Question",{"text":113,"@type":114},"MBTI-in-Thoughts enhances LLM agents by applying psychologically grounded personality conditioning. It uses MBTI archetypes to prime agents so their behavior becomes more effective and controllable across cognition and affect.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does MBTI-based priming affect agent behavior across tasks?",{"text":118,"@type":114},"Personality priming produces consistent, interpretable behavioral biases. Emotionally expressive “Feeling” types tend to excel in narrative generation, while “Thinking” types adopt more rigid yet consistent strategies in game-theoretic settings.",{"name":120,"@type":111,"acceptedAnswer":121},"What experimental mechanisms help cooperation and reasoning in multi-agent interactions?",{"text":122,"@type":114},"The framework supports structured multi-agent communication phases, including pre-communication reflection. It also finds that self-reflection prior to interaction improves cooperation and reasoning quality.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},293093,1789659502,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},1099523885074,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","Psychologically Enhanced AI Agents  \nMaciej Besta 1†, Shriram Chandran 1 , Robert Gerstenberger 1 , Mathis Lindner 1 , Marcin Chrapek 1 , Sebastian Hermann Martschat2 , Taraneh Ghandi2 * , Patrick Iff1 ,  \nHubert Niewiadomski3,4 , Piotr Nyczyk3,4 , Jrgen Mller2 , Torsten Hoefler 1  \n1ETH Zurich 2BASF SE 3 Cledar 4IDEAS Research Institute † Corresponding author  \narXiv :2509 .04343v 1 [ cs .AI] 4 Sep 2025  \nAbstract  \nWe introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers–Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks:  \nemotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhancedAI agents without any fine-tuning.  \nCode—[https://github.com/spcl/MBTI-in-Thoughts](https://github.com/spcl/MBTI-in-Thoughts)  \n1 Introduction  \nIn the rapidly evolving landscape of AI, Large Language Models (LLMs) are reshaping the way we interact with and perceive technology. These sophisticated models, with their vast linguistic capabilities, are redefining the possibilities of human-computer interaction. In this broad landscape, incontext learning (ICL) has become a new highly relevant area of research (Wu et al. 2022; Qiao et al. 2023; Besta et al. 2025c) . ICL is particularly attractive as it democratizes LLMs and their powerful capabilities as it is easy to use and try. It is also cost-effective and does not require expensive and time-consuming training. Enhancing ICL has thus become a goal of great significance.  \nAs LLMs become integral parts of our digital lives, their influence extends beyond mere functionality to the realm of  \n*At the time of publication, the author was a PhD student at McMaster university under a collaborative partnership program with BASF SE.  \npersonality (Serapio-Garc´ıa et al. 2025) . As a matter of fact, LLMs do exhibit behavior implying possessing certain traits, as illustrated by – for example – recent news of LLMs “just wanting to be liked” (Salecha et al. 2024) . Recent investigations delve into the diverse personality traits exhibited by LLMs, unraveling the intricate tapestry of their linguistic fabric. Numerous researchers, employing various personality frameworks, have scrutinized these models to uncover nuanced dimensions of behavior, researching whether LLMs can truly manifest personality traits akin to human nature (Serapio-Garc´ıa et al. 2025) . However, all these analyses and frameworks are mostly dedicated to analyzing and shaping the personalities of LLMs.  \nIn this work, we propose to integrate personality traits into LLM agents in order to enhance their effectiveness (contribution 1) . It is common psychological knowledge that different personality types often have special aptitude for tasks that others do not. For example, in the well-known Myers–Briggs 16 Personalities framework (MBTI) (Myers and Briggs 1944), “emotional” personality types such as ISFJ (“the Defender”) are known to be more effective in emotional support tasks than “logical” types such as ","cbCaiePrcsseL1Rl","https://ap.wps.com/l/cbCaiePrcsseL1Rl","pdf",5243900,37,"English","# Abstract\n# Introduction","[{\"question\":\"What is MBTI-in-Thoughts, and what does it enhance in LLM agents?\",\"answer\":\"MBTI-in-Thoughts enhances LLM agents by applying psychologically grounded personality conditioning. It uses MBTI archetypes to prime agents so their behavior becomes more effective and controllable across cognition and affect.\"},{\"question\":\"How does MBTI-based priming affect agent behavior across tasks?\",\"answer\":\"Personality priming produces consistent, interpretable behavioral biases. Emotionally expressive “Feeling” types tend to excel in narrative generation, while “Thinking” types adopt more rigid yet consistent strategies in game-theoretic settings.\"},{\"question\":\"What experimental mechanisms help cooperation and reasoning in multi-agent interactions?\",\"answer\":\"The framework supports structured multi-agent communication phases, including pre-communication reflection. It also finds that self-reflection prior to interaction improves cooperation and reasoning quality.\"}]","Psychologically Enhanced AI Agents | PDF",93]