[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84324-en":3,"doc-seo-84324-105":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},84324,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","ASMR: Agentic Schema Generation for Ship Maintenance Report Writing","This paper addresses automatic schema generation for ship maintenance and operational reports across multiple form categories, aiming to discover compact yet informative schemas that capture essential information requirements for each report type. It introduces ASMR, a modular agentic framework with a Field Generation Agent and a Structural Optimizer Agent. The field agent extracts semantic concepts from historical narratives via adaptive multi-granularity clustering, while the optimizer uses reinforcement learning to retain, merge, or discard fields. Output schemas improve report completeness, consistency, and actionable downstream analytics.","ASMR: Agentic Schema Generation for Ship Maintenance Report  \nWriting  \nSohrab Namazi Nia  \nNew Jersey Institute of Technology Newark, New Jersey, USA [sn773@njit.edu](sn773@njit.edu)  \nPeter Ly  \nRensselaer Polytechnic Institute Troy, New York, USA [lyp2@rpi.edu](lyp2@rpi.edu)  \nAmogh Dalal  \nNew Jersey Institute of Technology Newark, New Jersey, USA [asd33@njit.edu](asd33@njit.edu)  \nMarti Zentmaier  \nBoston Fusion Corporation Lexington, Massachusetts, USA [marti.zentmaier@bostonfusion.com](marti.zentmaier@bostonfusion.com)  \nNing Sa  \nRensselaer Polytechnic Institute Troy, New York, USA [san2@rpi.edu](san2@rpi.edu)  \nTomek Strzalkowski  \nRensselaer Polytechnic Institute Troy, New York, USA [tomek@rpi.edu](tomek@rpi.edu)  \nJay Miller  \nBoston Fusion Corporation Lexington, Massachusetts, USA [jay.miller@bostonfusion.com](jay.miller@bostonfusion.com)  \nRishi Singh  \nBoston Fusion Corporation Lexington, Massachusetts, USA [rishi.singh@bostonfusion.com](rishi.singh@bostonfusion.com)  \nSenjuti Basu Roy  \nNew Jersey Institute of Technology Newark, New Jersey, USA [senjutib@njit.edu](senjutib@njit.edu)  \narXiv :2607 .08 177v 1 [ cs .AI] 9 Jul 2026  \nABSTRACT  \nIn this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, automatically discover compact and informative schemas that capture the essential information requirements of each report type. To address this challenge, we propose ASMR, a modular agentic framework consisting of two specialized agents. A Field Generation Agent extracts semantic concepts from historical narratives and generates candidate schema fields through adaptive multi-granularity clustering, while a Structural Optimizer Agent employs reinforcement learning to identify compact, informative, and non-redundant schema representations. The resulting schemas can guide report authors toward producing more complete, consistent, and actionable reports. Preliminary results demonstrate the promise of the proposed approach and highlight several open research challenges at the intersection of data management, agentic AI, and human-centered AI.  \nVLDB Workshop Reference Format:  \nSohrab Namazi Nia, Amogh Dalal, Ning Sa, Peter Ly, Marti Zentmaier, Tomek Strzalkowski, Jay Miller, Rishi Singh, and Senjuti Basu Roy. ASMR: Agentic Schema Generation for Ship Maintenance Report Writing. VLDB 2026 Workshop: DASHSys: Systems for Data-centric Agents with Humanin-the-loop.  \n1 INTRODUCTION  \nMany ship operational and maintenance reporting workflows rely on forms that contain substantial unstructured textual narratives. Free-form text provides flexibility to describe critical operational information such as equipment conditions, hazards, mitigation actions, system failures, preservation activities, maintenance observations, and operational impacts. However, across different personnel with varying levels of expertise, this same flexibility can result in  \nThis work is licensed under the Creative Commons BY-NC-ND 4.0 International License.  \ninconsistent structure that makes it difficult to extract actionable insights from reports at scale. In particular, required information that goes unrecorded by personnel can be impossible to recover, which is a problem made worse in large enterprises where report writers are far removed from downstream report consumers. Instead of burdening personnel with more training that scales poorly across large workforces, we imagine real-time writing assistance that provides topic-specific information requirements to personnel during the writing process. This would better optimize tradeoffs between flexibility and structure provided by free-text inputs while supporting downstream workflows.  \nTo support such a capability, we formulate the schema generation problem: given a collection of historical reports, automatically discover schemas consisting of compact sets of information fields that capture e","cbCaittmNCkrFDs5","https://ap.wps.com/l/cbCaittmNCkrFDs5","pdf",6712650,1,9,"English","en",105,"# Introduction\n## Problem: schema generation from unstructured ship reports\n## ASMR approach: two specialized agents\n## Downstream benefits","[{\"question\":\"What problem does this paper focus on?\",\"answer\":\"It studies automatic schema generation from historical ship maintenance and operational reports, discovering compact schemas that reflect essential information requirements for each report type and topic.\"},{\"question\":\"How does ASMR generate candidate schema fields?\",\"answer\":\"A Field Generation Agent extracts semantic concepts from unstructured report narratives and uses adaptive multi-granularity clustering to propose candidate schema fields.\"},{\"question\":\"How does ASMR optimize the final schema?\",\"answer\":\"A Structural Optimizer Agent treats schema construction as sequential decision-making and applies reinforcement learning to iteratively retain, merge, or discard fields to maximize coverage and informativeness while minimizing redundancy and keeping schemas compact.\"}]",1784194827,23,{"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},"asmr-agentic-schema-generation-for-ship-maintenance-report-writing","",{"@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/asmr-agentic-schema-generation-for-ship-maintenance-report-writing/84324/",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 problem does this paper focus on?","Question",{"text":75,"@type":76},"It studies automatic schema generation from historical ship maintenance and operational reports, discovering compact schemas that reflect essential information requirements for each report type and topic.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ASMR generate candidate schema fields?",{"text":80,"@type":76},"A Field Generation Agent extracts semantic concepts from unstructured report narratives and uses adaptive multi-granularity clustering to propose candidate schema fields.",{"name":82,"@type":73,"acceptedAnswer":83},"How does ASMR optimize the final schema?",{"text":84,"@type":76},"A Structural Optimizer Agent treats schema construction as sequential decision-making and applies reinforcement learning to iteratively retain, merge, or discard fields to maximize coverage and informativeness while minimizing redundancy and keeping schemas compact.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":21,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]