[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85223-en":3,"doc-seo-85223-105":30,"detail-sidebar-cat-0-en-105":92},{"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},85223,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","RecRec Recursive Refinement for Sequential Recommendation","Sequential recommender systems typically derive user preferences from historical interaction sequences using single-pass encoding, which limits their ability to iteratively correct preference representations and recover from approximation errors. RecRec (Recursive Recommendation) rethinks sequential recommendation as recursive latent state inference, maintaining a compact persistent preference state and refining it through a shared recursive module. An evidence-anchored correction mechanism stabilizes updates by grounding each refinement in the original interaction context, preventing semantic drift. Experiments on three benchmarks match or exceed strong baselines with 3.9M–14M parameters.","RecRec: Recursive Refinement for Sequential Recommendation  \nPervez Shaik  \n[shaik.pervez@sony.com](shaik.pervez@sony.com)[ ](shaik.pervez@sony.com)Sony Research India India  \nProsenjit Biswas  \n[prosenjit.biswas@sony.com](prosenjit.biswas@sony.com)[ ](prosenjit.biswas@sony.com)Sony Research India India  \nAbhinav Thorat  \n[Abhinav.Thorat@sony.com](Abhinav.Thorat@sony.com)[ ](Abhinav.Thorat@sony.com)Sony Research India India  \nRavi Kolla  \n[ravi.kolla@sony.com](ravi.kolla@sony.com)[ ](ravi.kolla@sony.com)Sony Research India India  \nNiranjan Pedanekar  \n[niranjan.pedanekar@sony.com](niranjan.pedanekar@sony.com)[ ](niranjan.pedanekar@sony.com)Sony Research India India  \narXiv :2607 . 1054 1v 1 [ cs .IR] 12 Jul 2026  \nAbstract  \nSequential recommender systems typically infer user preferences through single-pass encoding of interaction histories without iterative refinement, relying on increasingly deep architectures to capture complex patterns. In this work, we revisit sequential recommendation from a recursive inference perspective: can user preferences be modeled as a persistent latent state that is recursively refined? We propose RecRec (Recursive Recommendation), a lightweight model that maintains a compact latent state and updates it through a shared recursive module conditioned on interaction evidence. Unlike prior recursive models, RecRec introducesan evidence-anchored correction mechanism that stabilizes refinement by grounding each update in the original interaction context, preventing semantic drift during deep recursive reasoning. Experiments on three benchmark datasets under standard evaluation protocols show that RecRec matches or outperforms state-of-the-art sequential, graph-based, and reasoning-enhanced recommenders while using only 3.9M to 14M parameters. Ablation studies demonstrate that both recursive refinement and the evidence-anchored correction gate contribute significantly to performance, highlighting the effectiveness of recursive latent inference as a scalable alternative to deeper or language-based architectures. Code is available here.  \nKeywords  \nRecommendation Systems, Sequential Recommendation, Recursive Models, Preference Modeling  \n1 Introduction  \nSequential recommender systems aim to infer user preferences from historical interaction sequences to predict the next relevant item. Existing approaches primarily enhance sequence modeling capacity through Markov models [4, 17], recurrent networks [13], and Transformer-based architectures [10, 15] . These methods encode interaction histories in a single forward pass, relying on deeper architectures to capture complex behavioral patterns, lacking mechanisms to iteratively refine or correct preference representations once computed. Consequently, they are limited in their ability to progressively improve estimates or recover from approximation errors. On the other hand, recent reasoning-enhanced approaches based on large and small language models [2, 3, 25] enable multistep reasoning and inference, but incur substantial computational overhead and rely on token space of the language models.  \nIn this work, we revisit sequential recommendation problem from a recursive inference perspective and ask: can user preferences be modeled as a persistent latent state that is recursively refined? We propose RecRec (Recursive Recommendation), a lightweight model that maintains a compact latent state and updates it through a shared recursive module conditioned on interaction evidence, enabling progressive refinement beyond single-pass encoding. A key challenge in recursive refinement is semantic drift, where accumulated approximation errors during recursive updates cause representations to deviate from the original evidence. To address this, we introduce an evidence-anchored correction mechanism that grounds each update in the interaction context, ensuring stable refinement. Our approach is inspired by the Tiny Recursive Model (TRM) [9], but differs by focusing on corr","cbCaijHaqdFmwx3b","https://ap.wps.com/l/cbCaijHaqdFmwx3b","pdf",911032,6,1,7,"English","en",105,"# Abstract\n# Introduction\n# Related Work\n## Sequential Recommendation\n## Latent Representation and Reasoning","[{\"question\":\"What problem does RecRec address in sequential recommender systems?\",\"answer\":\"RecRec targets the limitation of single-pass sequential encoders that cannot iteratively refine or correct preference representations after they are computed, making them less able to improve estimates or recover from errors.\"},{\"question\":\"How does RecRec model user preferences?\",\"answer\":\"It treats user preferences as a persistent latent state that is recursively refined over multiple steps rather than inferred once via one forward pass.\"},{\"question\":\"What prevents semantic drift during recursive refinement?\",\"answer\":\"RecRec introduces an evidence-anchored correction mechanism that grounds each recursive update in the original interaction context, stabilizing refinement and preventing accumulated approximation errors from drifting the representation.\"}]",1784201840,18,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"recrec-recursive-refinement-for-sequential-recommendation","",{"@graph":36,"@context":86},[37,54,69],{"@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":53},"https://docshare.wps.com/document/recrec-recursive-refinement-for-sequential-recommendation/85223/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does RecRec address in sequential recommender systems?","Question",{"text":76,"@type":77},"RecRec targets the limitation of single-pass sequential encoders that cannot iteratively refine or correct preference representations after they are computed, making them less able to improve estimates or recover from errors.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does RecRec model user preferences?",{"text":81,"@type":77},"It treats user preferences as a persistent latent state that is recursively refined over multiple steps rather than inferred once via one forward pass.",{"name":83,"@type":74,"acceptedAnswer":84},"What prevents semantic drift during recursive refinement?",{"text":85,"@type":77},"RecRec introduces an evidence-anchored correction mechanism that grounds each recursive update in the original interaction context, stabilizing refinement and preventing accumulated approximation errors from drifting the representation.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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":107,"slug":137},19,"General","general"]