[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85576-en":3,"doc-seo-85576-105":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},85576,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Algorithm Selection with Zero Domain Knowledge via Text Embeddings","Algorithm Selection with ZeroFolio presents a feature-free framework that chooses a solver for a problem instance using pretrained text embeddings rather than hand-crafted instance features. The pipeline serializes each raw instance as plain text, embeds it with an off-the-shelf embedding model, and applies weighted k-nearest neighbors to predict algorithm choice. Experiments on 11 ASlib scenarios across seven domains show consistent gains over random-forest baselines, robustness to serialization seeds, and competitiveness with AutoFolio without per-scenario tuning.","arXiv :2604 . 19753v2 [ cs .AI] 11 Jul 2026  \nAlgorithm Selection with Zero Domain Knowledge via  \nText Embeddings  \nStefan Szeider  \nAlgorithms and Complexity Group  \nTU Wien, Vienna, Austria  \n[www.ac.tuwien.ac.at/people/szeider/](www.ac.tuwien.ac.at/people/szeider/)  \nAbstract  \nWe propose a feature-free approach to algorithm selection: instead of hand-crafted instance features, we use pretrained text embeddings. Our method, ZeroFolio, proceeds in three steps. First, it reads the raw instance file as plain text. Second, it embedsit with a pretrained embedding model. Third, it selects an algorithm via weighted k-nearest neighbors. The key to our approach is the fact that pretrained embeddings can distinguish problem instances without any domain knowledge or task-specific training. Hence, we can apply the same three-step pipeline (serialize, embed, select) across any problem domain with text-based instance formats. We evaluate our approach on 11 ASlib scenarios spanning 7 domains (SAT, MaxSAT, QBF, ASP, CSP, MIP, and graph problems) . Our experiments show that this approach outperforms a random forest trained on hand-crafted features in 9 of 11 scenarios, robustly across serialization seeds (every seed, not just a favorable one) and often by a substantial margin; it still wins 8 of  \n11 against a per-scenario-tuned random forest. On the three scenarios with published AutoFolio results from the 2015 ASlib competition, ZeroFolio comes within a small margin of AutoFolio without any per-scenario configuration tuning. Our ablation study shows that inverse-distance weighting, line shuffling, and Manhattan distance are the key design choices, and we analyze the sensitivity of the selector to the serialization seed. On SAT12-ALL, where both selectors are competitive, combining embeddings with hand-crafted features via soft voting yields a further improvement.  \n1 Introduction  \nAlgorithm selection is the fundamental problem of choosing a solver from a portfolio of solvers for a given problem instance. Rice (1976) formalized this problem as a mapping from instance features to algorithm performance. The framework guided the research for fifty years.  \nModern algorithm selection systems utilize hand-crafted features and train machine learning models to predict solver runtimes. SATzilla (Xu et al., 2008) pioneered featurebased algorithm selection for SAT. This was later automated by AutoFolio (Lindauer et al. , 2015) . The ASlib benchmark library (Bischl et al., 2016) provides a standardized evaluation framework with precomputed features on various scenarios over several domains.  \nThe central challenge of standard algorithm selection approaches is domain-specific feature engineering. Each new domain requires expert knowledge to design informative features. Computing the features can itself be a costly task. For instance, SATzilla’s probing features run SAT solvers internally and can time out or crash on hard instances. Shavit and Hoos (2024) recently updated the SATzilla feature extractor. They report that the original tool failed to extract features from over 20% of modern SAT competition instances. Moreover,  \nfeatures designed for one domain (e.g., clause-variable ratios for SAT) rarely carry over to other domains (e.g., constraint satisfaction or answer set programming) . This provides a trade-off to practitioners: on the one hand, they invest in domain-specific feature engineering; on the other, they accept weaker selection performance.  \nWe propose a novel approach that does not require any feature engineering. The basic idea is to read the raw instance file as plain text, embed it with a pretrained, off-the-shelf text embedding model, and subsequently select an algorithm via weighted k-nearest neighbors. Our results show that pretrained embeddings produce representations that distinguish instance structures well enough for effective algorithm selection. This works without any task-specific training or feature engineering.  \nIt is","cbCaifVpSMoHOJUD","https://ap.wps.com/l/cbCaifVpSMoHOJUD","pdf",611780,1,14,"English","en",105,"# Abstract\n# Introduction\n# Related Work","[{\"question\":\"What problem does ZeroFolio address in algorithm selection?\",\"answer\":\"ZeroFolio targets the domain-specific feature engineering bottleneck in algorithm selection by avoiding hand-crafted instance features and using pretrained text embeddings instead.\"},{\"question\":\"How does ZeroFolio select an algorithm from a given instance?\",\"answer\":\"It serializes the raw instance file as plain text, computes a pretrained embedding, and then performs weighted k-nearest neighbors to choose the algorithm.\"},{\"question\":\"How does ZeroFolio perform compared with feature-based baselines and AutoFolio?\",\"answer\":\"On 11 ASlib scenarios, it outperforms a random forest trained on hand-crafted features in 9 scenarios, and it still wins 8 of 11 when that random forest is tuned per scenario; against AutoFolio, it comes within a small margin on the three scenarios with published results without per-scenario tuning.\"}]",1784204699,35,{"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},"algorithm-selection-with-zero-domain-knowledge-via-text-embeddings","",{"@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/algorithm-selection-with-zero-domain-knowledge-via-text-embeddings/85576/",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","2026-07-25","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 ZeroFolio address in algorithm selection?","Question",{"text":75,"@type":76},"ZeroFolio targets the domain-specific feature engineering bottleneck in algorithm selection by avoiding hand-crafted instance features and using pretrained text embeddings instead.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does ZeroFolio select an algorithm from a given instance?",{"text":80,"@type":76},"It serializes the raw instance file as plain text, computes a pretrained embedding, and then performs weighted k-nearest neighbors to choose the algorithm.",{"name":82,"@type":73,"acceptedAnswer":83},"How does ZeroFolio perform compared with feature-based baselines and AutoFolio?",{"text":84,"@type":76},"On 11 ASlib scenarios, it outperforms a random forest trained on hand-crafted features in 9 scenarios, and it still wins 8 of 11 when that random forest is tuned per scenario; against AutoFolio, it comes within a small margin on the three scenarios with published results without per-scenario tuning.","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"]