[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273657-105":59,"doc-detail-273657-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","time-series-retrieval-for-grounding-multimodal-language-models-in-remaining-useful-life-prediction-abstract-and-introduction","Time-Series Retrieval for Grounding Multimodal Language Models in Remaining Useful Life Prediction - Abstract and Introduction","","Large language models and agentic AI systems are increasingly applied to domain-specific maintenance and prognostics, motivating an investigation of how multimodal large language models can estimate remaining useful life (RUL) when grounded by time-series retrieval. The study proposes a framework that retrieves historically similar degradation segments, builds a visual comparison artifact with the test trajectory, and uses a structured multimodal prompt for inference. Experiments on FD001 of the C-MAPSS benchmark show consistent error reduction and more stable performance versus random-reference baselines, with gains depending on model capacity and practical limitations in PHM settings.",{"@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/time-series-retrieval-for-grounding-multimodal-language-models-in-remaining-useful-life-prediction-abstract-and-introduction/273657/",{"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/time-series-retrieval-for-grounding-multimodal-language-models-in-remaining-useful-life-prediction-abstract-and-introduction/273657.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-25","2026-09-15",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 problem does the paper address?","Question",{"text":113,"@type":114},"The paper studies whether time-series retrieval improves multimodal large language model (MLLM) estimation of remaining useful life (RUL).","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed retrieval-based framework work?",{"text":118,"@type":114},"Historically similar degradation segments are retrieved, combined with the test trajectory into a visual comparison artifact, and processed by the MLLM using a structured multimodal prompt.",{"name":120,"@type":111,"acceptedAnswer":121},"What datasets and baselines are used to evaluate the method?",{"text":122,"@type":114},"Evaluation uses the FD001 partition of the C-MAPSS benchmark and compares retrieval-based inference against a non-retrieval baseline that selects random references.","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},273657,1789472391,{"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},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Time-Series Retrieval for Grounding Multimodal Language Models  \nin Remaining Useful Life Prediction  \narXiv : 2608 . 192 18v2 [cs .CL] 23 Aug 2026  \nValeriu Dimidov and Raphal Frank  \nInterdisciplinary Centre for Security, Reliability and Trust (SnT) University of Luxembourg  \n29 Avenue J.F. Kennedy L-1855, Luxembourg  \n[firstname.lastname@uni.lu](firstname.lastname@uni.lu)  \nABSTRACT  \nLarge language models (LLMs) and agentic AI systems are increasingly being explored for domain-specific maintenance and prognostics tasks, raising the question of whether they can effectively support prognostics and health management (PHM) . In this paper, we investigate remaining useful life (RUL) estimation with multimodal large language models (MLLMs) grounded through time-series retrieval. We propose a framework in which historically similar degradation segments are retrieved from the training set and, together with the test trajectory, transformed into a visual comparison artifact that is processed by the MLLM through a structured multimodal prompt. The approach is evaluated on the FD001 partition of the C-MAPSS benchmark under repeated experiments comparing retrieval-based inference against anon-retrieval baseline based on random reference selection. The results show that time-series retrieval consistently improves MLLM-based RUL prediction across the evaluated models, yielding lower error and more stable performance. At the same time, the magnitude of the benefit depends on model capacity, indicating that retrieval is most effective when the underlying MLLM is able to exploit the retrieved evidence. Overall, the study shows that time-series RAG is a promising mechanism for improving multimodal prognostic reasoning, while also highlighting the current limitations of MLLM-based RUL estimation in practical PHM settings.  \n1. INTRODUCTION  \nPredictive Maintenance (PdM) aims to reduce downtime, maintenance costs, and operational risks by anticipating failures before they occur. A key task in this context is Remaining Useful Life (RUL) estimation, which provides an estimate of the time left before a component reaches failure. Accurate RUL estimation supports maintenance planning,  \nValeriu Dimidov et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nresource allocation, and risk-aware decision making in Prognostics and Health Management (PHM) .  \nConventional RUL estimation methods are typically based on statistical degradation models, physics-informed approaches, or data-driven architectures trained on sensor time series. Although these methods can achieve strong predictive performance, they usually operate only on numerical data and provide limited support for reasoning over external contextual knowledge.  \nRecent advances in large language models (LLMs) and multimodal large language models (MLLMs) create an opportunity to revisit RUL estimation from a different perspective (Zhang, Chowdhury, Gupta, & Shang, 2024; Yin et al., 2024) . Instead of relying only on a learned numerical predictor, an MLLM can be prompted with visual and textual evidence describing the target trajectory. Retrieval-augmented generation (RAG) can further enrich this input by selecting historical degradation segments that are similar to the query trajectory, following the broader idea of grounding language-model generation with retrieved external evidence (Lewis et al., 2020) . However, in the RUL setting, the effect of such retrieval is not obvious: relevant references may ground the model on useful degradation evidence, whereas poorly matched references may introduce noise or bias the prediction.  \nTherefore, this paper studies whether time-series retrieval improves MLLM-based RUL estimation. We propose a framework in which similar degradation segments are ret","cbCaio1zVwq651Dd","https://ap.wps.com/l/cbCaio1zVwq651Dd","pdf",5999601,11,"English","# Abstract\n# Introduction\n# Related Work","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper studies whether time-series retrieval improves multimodal large language model (MLLM) estimation of remaining useful life (RUL).\"},{\"question\":\"How does the proposed retrieval-based framework work?\",\"answer\":\"Historically similar degradation segments are retrieved, combined with the test trajectory into a visual comparison artifact, and processed by the MLLM using a structured multimodal prompt.\"},{\"question\":\"What datasets and baselines are used to evaluate the method?\",\"answer\":\"Evaluation uses the FD001 partition of the C-MAPSS benchmark and compares retrieval-based inference against a non-retrieval baseline that selects random references.\"}]","Time-Series Retrieval for Grounding Multimodal Language Models in Remaining Useful Life Prediction - Abstract and Introduction | PDF",28]