[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84733-en":3,"doc-seo-84733-105":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},84733,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Autonomous Information Seeking A Roadmap for Agentic Recommender Systems","Large language model agents are reshaping recommender systems from static ranking pipelines into autonomous, interactive systems that can reason, plan, and act. This survey introduces a unified taxonomy based on autonomy level and three agentic paradigms: agent-assisted recommendation, agent-as-recommender, and agent-as-user simulator. It analyzes architecture choices for profiles, memory, tool use, workflows, and optimization. It reviews evaluation methods and highlights open problems in trajectory assessment, contribution analysis, calibration of user simulation, lifelong modeling, alignment, controllability, trust, privacy, scalability, and efficiency.","arXiv :2607 .04433v 1 [ cs .IR] 5 Jul 2026  \nAutonomous Information Seeking: A Roadmap for Agentic Recommender Systems  \nXinyu Lin1 Yashar Deldjoo2 B Sunhao Dai3 Honghui Bao1 Xiaopeng Ye3 Fatemeh Nazary2 Wenjie Wang4 Tommaso Di Noia2 Jun Xu3 Tat-Seng Chua1  \n1National University of Singapore 2Polytechnic University of Bari  \n3Renmin University of China 4University of Science and Technology of China  \n[xylin1028@gmail.com](xylin1028@gmail.com) , [deldjooy@acm.org](deldjooy@acm.org)  \nThe rapid integration of large language model-based agents into recommender systems has driven a shift from static, ranking-based pipelines toward autonomous and interactive systems that can reason, plan, and act. This survey provides a comprehensive overview of this emerging landscape by introducing a unified taxonomy grounded in the level of autonomy and three core paradigms of agentic recommender systems: agent-assisted recommendation, agent-asrecommender, and agent-as-user-simulator. The autonomy framework organizes existing methods along increasing capabilities in proactivity, context awareness, interaction flexibility, and adaptivity. Building on this framework, the survey analyzes how each paradigm adopts different agentic architectures and how agents enhance key components such as profiles, memory, tool use, workflows, and optimization mechanisms. We further examine evaluation methodologies for agentic recommendation, covering automated metrics, LLM-based judging, and simulation-based assessment, and discuss their limitations in capturing reasoning quality, user experience, and system behavior. Beyond existing evaluation protocols, we further discuss unresolved issues in evaluating agentic recommender systems, including trajectorylevel assessment, agent contribution analysis, and calibration of user simulation. Lastly, the survey outlines open challenges in lifelong user modeling, contextual abstraction, multimodal alignment, controllability, trustworthiness, privacy, scalability, and efficiency. Together, these analyses establish a unified foundation for understanding the current progress of agentic recommender systems and highlight promising opportunities for developing more autonomous, reliable, and human-aligned recommendation agents.  \nKeywords: Agentic Recommender System, Level of Autonomy, LLM Agent, Agentassisted Recommender, Agent as Recommender, Agent as User Simulator  \nB Corresponding author.  \n1. Introduction  \nRecommender systems (RS) have traditionally been evaluated by how accurately they predict user preferences and rank items based on historical user–item interactions. Classical approaches—from collaborative filtering to modern deep retrieval and ranking architectures trained on clicks, ratings, and purchases—encode past behavior into latent representations and, given a user and context, output a ranked list of candidate items. This paradigm is highly effective for the dominant interaction pattern in today’s platforms: the system curates options and the user chooses among them (e.g., selecting a movie from a ranked homepage list) .  \nTable 1 | Modernized comparison of recommender system paradigms.  \nDimension Classical RS LLM-based RS (generative / Agentic RS  \nprompt-based)  \n\n| Recommendation Goal | Personalized ranking: match past user–item interactions via shallow user models. | Personalized ranking & language generation: infer preferences via prompts and generate textual outputs. | Goal-oriented decision support: produce recommendations under constraints via multi-step reasoning and actions. |\n| --- | --- | --- | --- |\n| Proactivity | Reactive: suggest only when RS is explicitly requested. | Mostly reactive: respond to prompts and conversational requests. | Mixed-initiative potential: be able to ask clarifying questions, propose plans, and surface trade-offs. |\n| Context Awareness | Limited to behavior logs and static features. | Uses context within the LLM’s window with optional retrieved snippets. | Situational & to","cbCaigsIAL1PocGB","https://ap.wps.com/l/cbCaigsIAL1PocGB","pdf",1381107,1,45,"English","en",105,"# Introduction\n## Modern recommender system paradigms comparison\n## Survey scope and taxonomy of agentic recommenders","[{\"question\":\"What change does the survey highlight in recommender systems with LLM-based agents?\",\"answer\":\"It highlights a shift from static, ranking-focused pipelines to autonomous and interactive systems that can reason, plan, and act rather than only producing a ranked list.\"},{\"question\":\"What are the three core paradigms of agentic recommender systems introduced in the survey?\",\"answer\":\"The survey organizes approaches into agent-assisted recommendation, agent-as-recommender, and agent-as-user simulator, each targeting different interaction and decision-support patterns.\"},{\"question\":\"How does the survey evaluate agentic recommendation systems and what are key limitations?\",\"answer\":\"It covers automated metrics, LLM-based judging, and simulation-based assessment, noting that these methods may not fully capture reasoning quality, user experience, or system behavior.\"}]",1784197934,113,{"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},"autonomous-information-seeking-a-roadmap-for-agentic-recommender-systems","",{"@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/autonomous-information-seeking-a-roadmap-for-agentic-recommender-systems/84733/",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","2026-07-17","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 change does the survey highlight in recommender systems with LLM-based agents?","Question",{"text":75,"@type":76},"It highlights a shift from static, ranking-focused pipelines to autonomous and interactive systems that can reason, plan, and act rather than only producing a ranked list.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the three core paradigms of agentic recommender systems introduced in the survey?",{"text":80,"@type":76},"The survey organizes approaches into agent-assisted recommendation, agent-as-recommender, and agent-as-user simulator, each targeting different interaction and decision-support patterns.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the survey evaluate agentic recommendation systems and what are key limitations?",{"text":84,"@type":76},"It covers automated metrics, LLM-based judging, and simulation-based assessment, noting that these methods may not fully capture reasoning quality, user experience, or system behavior.","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"]