[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83594-en":3,"doc-seo-83594-105":29,"detail-sidebar-cat-0-en-105":82},{"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},83594,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",6,"Technology","CADENZA in Action Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries","Semantic query processing engines execute semantic operators whose behavior is defined by natural-language intents and carried out through model inference over multimodal data. Existing optimizers mainly tune monolithic operator implementations, creating a costly trade-off between expensive model calls and cheaper methods that miss intent-dependent semantics. CADENZA compiles each intent into decomposed steps, selects physical implementations, and optimizes parameters according to user quality–latency–cost preferences. The web demo explores plan decomposition, plan optimization, and preference-driven selection across multimodal databases.","CADENZA in Action: Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries  \nJaehyun Ha  \n[jhha@dblab.postech.ac.kr](jhha@dblab.postech.ac.kr)[ ](jhha@dblab.postech.ac.kr)GSAI, POSTECH Pohang, Korea  \nYongjoo Park  \n[yongjoo@illinois.edu](yongjoo@illinois.edu)[ ](yongjoo@illinois.edu)Univ. of Illinois Urbana-Champaign Urbana, USA  \nWook-Shin Han∗  \n[wshan@dblab.postech.ac.kr](wshan@dblab.postech.ac.kr)[ ](wshan@dblab.postech.ac.kr)GSAI, POSTECH Pohang, Korea  \narXiv :2607 .0 1468v 1 [ cs .DB] 1 Jul 2026  \nAbstract  \nSemantic query processing engines execute semantic operators, whose behavior is specified by natural-language intents, via model inference over multimodal data. Most existing optimizers optimize the operators at the granularity of monolithic implementations—such as LLMs and embedding models—forcing a trade-off between expensive model calls and cheaper alternatives that fail to capture intent-dependent semantics. We present CADENZA, a semantic operator optimizer that compiles an intent into decomposed steps, selects concrete physical implementations for each step, and tunes their parameters under user-specified quality–latency–cost preferences. In this demonstration, users interact with CADENZA through a web interface over multimodal databases, exploring how an intent is decomposed into alternative plans, how each plan is optimized, and how different preferences yield different winning plans.  \nPVLDB Reference Format:  \nJaehyun Ha, Yongjoo Park, and Wook-Shin Han. CADENZA in Action: Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries. PVLDB, 19(12): XXX-XXX, 2026 .  \ndoi:XX.XX/XXX.XX  \nPVLDB Artifact Availability:  \nThe source code, data, and/or other artifacts have been made available at [https://github.com/postechdblab/CADENZA](https://github.com/postechdblab/CADENZA).  \n1 Introduction  \nWith the advent of Large Language Models (LLMs), a new class of semantic query processing engines (SQPEs) has emerged [4, 5, 8, 10, 11] . Semantic operators—such as SemFilter, SemJoin, and SemMap—are operators whose behaviors are specified by natural-language task descriptions (i.e., intents) and executed via model inference over multimodal data (e.g., text and images). These operators simplify complex multimodal analysis. For example, suppose an e-commerce platform onboards a vendor who delivers product descriptions (text with brand, category, specs, etc.) and product photos (images with logos but no metadata) as databases with no shared identifier. To build a unified catalog, a data engineer can execute a SemJoin to“match product descriptions with product photos of the same brand.”  \nMost existing semantic query optimizers [4, 5, 8–11] optimize at the granularity of a monolithic operator implementation—e.g.,  \n∗ Corresponding author.  \nThis work is licensed under the Creative Commons BY-NC-ND 4.0 International License. Visit [https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of](https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of)[ ](https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of)[this license. For any use beyond those covered by this license](this license. For any use beyond those covered by this license), [obtain permission by](obtain permission by)[emailing info@vldb.org. Copyright](emailing info@vldb.org. Copyright) is held by the owner/author(s). Publication rights licensed to the VLDB Endowment.  \nProceedings of the VLDB Endowment, Vol. 19, No. 12 ISSN 2150-8097 . doi:XX.XX/XXX.XX  \n(C)  \n\n| SCAN(images) | image | ImgObj | object | 􀀡5+9$4! %)5:5 |\n| --- | --- | --- | --- | --- |\n|  |  |  |  |  |\n\n\n| SCAN(desc) | desc | TxtNER | entity, | 􀀡!\"\\#$ %&'( |\n| --- | --- | --- | --- | --- |\n|  |  |  | type |  |\n\n| TxtImgSim | score | 􀀡3456$78 |\n| --- | --- | --- |\n|  |  |  |\n\nFigure 1: Three candidate logical plans for SemJoin with“match product descriptions with product photos of the same brand.” Each node is an operator and each ","cbCaimZh3rl3w43S","https://ap.wps.com/l/cbCaimZh3rl3w43S","pdf",2629147,1,4,"English","en",105,"# Introduction\n## Semantic query processing and intent-based operators\n## Limitations of monolithic optimizers\n## CADENZA: intent decomposition and plan optimization","[{\"question\":\"How are different execution plans selected for a user’s preferences?\",\"answer\":\"CADENZA optimizes parameters under user-specified quality–latency–cost preferences, leading to different winning plans among alternative decompositions for the same intent.\"}]",1784189080,10,{"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":77,"head_meta":79,"extra_data":81,"updated_unix":27},"cadenza-in-action-breaking-the-monolith-with-intent-dependent-plan-spaces-for-semantic-queries","",{"@graph":35,"@context":76},[36,52,67],{"@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/technology/",3,{"item":51,"name":13,"@type":42,"position":21},"https://docshare.wps.com/document/cadenza-in-action-breaking-the-monolith-with-intent-dependent-plan-spaces-for-semantic-queries/83594/",{"url":51,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"How are different execution plans selected for a user’s preferences?","Question",{"text":74,"@type":75},"CADENZA optimizes parameters under user-specified quality–latency–cost preferences, leading to different winning plans among alternative decompositions for the same intent.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,104,109,114,119,122,125],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":102,"slug":103},50,"technology",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},7,"Healthcare",40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":28,"slug":124},"Lifestyle","lifestyle",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":97,"slug":128},19,"General","general"]