{"id":"https://openalex.org/W7203774785","doi":"https://doi.org/10.48550/arxiv.2608.17170","title":"Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection","display_name":"Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203774785","doi":"https://doi.org/10.48550/arxiv.2608.17170"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17170","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17170","pdf_url":"https://arxiv.org/pdf/2608.17170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.17170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128652176","display_name":"Hai Xia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Xia, Hai","raw_affiliation_strings":["Algorithms and Complexity Group , TU Wien , Vienna , Austria,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithms and Complexity Group , TU Wien , Vienna , Austria,","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039752849","display_name":"Carlos Ans\u00f3tegui","orcid":"https://orcid.org/0000-0001-7727-2766","observed_orcids":["https://orcid.org/0000-0001-7727-2766"]},"institutions":[{"id":"https://openalex.org/I15766328","display_name":"Universitat de Lleida","ror":"https://ror.org/050c3cw24","country_code":"ES","type":"education","lineage":["https://openalex.org/I15766328"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ans\u00f3tegui, Carlos","raw_affiliation_strings":["Logic & Optimization Group , University of Lleida , Lleida , Spain,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Logic & Optimization Group , University of Lleida , Lleida , Spain,","institution_ids":["https://openalex.org/I15766328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037092803","display_name":"Stefan Szeider","orcid":"https://orcid.org/0000-0001-8994-1656","observed_orcids":["https://orcid.org/0000-0001-8994-1656"]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Szeider, Stefan","raw_affiliation_strings":["Algorithms and Complexity Group , TU Wien , Vienna , Austria,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithms and Complexity Group , TU Wien , Vienna , Austria,","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.010099999606609344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/algorithm-selection","display_name":"algorithm selection","score":0.9309999942779541},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"constraint satisfaction","score":0.9459999799728394},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9340000152587891},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.875},{"id":"https://openalex.org/keywords/interpretable-feature-extraction","display_name":"interpretable feature extraction","score":0.746999979019165},{"id":"https://openalex.org/keywords/minizinc","display_name":"MiniZinc","score":0.7649999856948853},{"id":"https://openalex.org/keywords/graph-representation","display_name":"graph representation","score":0.5759999752044678},{"id":"https://openalex.org/keywords/solver-portfolios","display_name":"solver portfolios","score":0.5299999713897705},{"id":"https://openalex.org/keywords/vehicle-routing-problem","display_name":"vehicle routing","score":0.8859999775886536},{"id":"https://openalex.org/keywords/car-sequencing","display_name":"car sequencing","score":0.9940000176429749},{"id":"https://openalex.org/keywords/error-correcting-codes","display_name":"error-correcting codes","score":0.8199999928474426},{"id":"https://openalex.org/keywords/combinatorial-optimization","display_name":"combinatorial optimization","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408000230789185},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7225000262260437},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.4754999876022339},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.47380000352859497},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.435699999332428},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4219000041484833},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.3452000021934509},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.2529999911785126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17170","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17170","pdf_url":"https://arxiv.org/pdf/2608.17170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.17170","doi":"https://doi.org/10.48550/arxiv.2608.17170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17170","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.17170","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17170","pdf_url":"https://arxiv.org/pdf/2608.17170","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3098964846","display_name":"Structure Identification with SAT (STRIDES)","funder_award_id":"P36420","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G4125750076","display_name":null,"funder_award_id":"10.55776/COE12","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G630843984","display_name":"Logics for Computer Science Program at TU Wien","funder_award_id":"101034440","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7635477404","display_name":"Bilateral Artificial Intelligence","funder_award_id":"COE12","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G8590477180","display_name":null,"funder_award_id":"10.55776","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G8920660035","display_name":null,"funder_award_id":"PID2022","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203774785.pdf","grobid_xml":"https://content.openalex.org/works/W7203774785.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1903307127"],"related_works":["https://openalex.org/W2137915473","https://openalex.org/W7098023364","https://openalex.org/W7221185800","https://openalex.org/W1750419207","https://openalex.org/W4403781046","https://openalex.org/W4401024495","https://openalex.org/W7161014301","https://openalex.org/W7215073662","https://openalex.org/W7160299828","https://openalex.org/W4225327711"],"abstract_inverted_index":{"Algorithm":[0],"selection":[1],"for":[2],"constraint":[3,89],"satisfaction":[4],"problems":[5,98],"requires":[6],"extracting":[7],"features":[8,125],"that":[9,36,52,72,119],"capture":[10],"problem":[11,28],"structure.":[12],"Manually":[13],"designing":[14],"feature":[15,57,147],"extractors":[16,115,148],"demands":[17],"deep":[18],"domain":[19],"expertise":[20],"and":[21,64,78,88,136],"quickly":[22],"becomes":[23],"a":[24,60,74,107],"bottleneck":[25],"when":[26],"new":[27],"classes":[29],"appear.":[30],"We":[31,91],"present":[32],"an":[33,43,65],"automated":[34],"approach":[35,94],"uses":[37],"Large":[38],"Language":[39],"Models":[40],"(LLMs)":[41],"in":[42],"agentic":[44],"check--fix--verify":[45],"loop":[46],"to":[47,127],"synthesize":[48],"executable":[49],"Python":[50],"scripts":[51],"act":[53],"as":[54,83],"interpretable,":[55],"problem-specific":[56],"extractors.":[58],"Given":[59],"high-level":[61],"MiniZinc":[62],"model":[63],"instance,":[66],"the":[67,137,143,145],"LLM":[68],"agent":[69],"generates":[70],"code":[71],"constructs":[73],"typed":[75],"graph":[76,84],"representation":[77],"computes":[79],"structural":[80],"properties":[81],"such":[82],"density,":[85],"variable":[86],"clustering,":[87],"tightness.":[90],"evaluate":[92],"our":[93],"on":[95,134],"three":[96],"combinatorial":[97],"(vehicle":[99],"routing,":[100],"car":[101],"sequencing,":[102],"fixed-length":[103],"error-correcting":[104],"codes)":[105],"with":[106],"portfolio":[108],"of":[109],"five":[110],"state-of-the-art":[111],"solvers.":[112],"The":[113],"synthesized":[114,146],"yield":[116],"algorithm":[117],"selectors":[118],"consistently":[120],"outperform":[121],"both":[122],"expert-curated":[123],"mzn2feat":[124],"(up":[126],"$8.3$":[128],"percentage":[129],"points":[130],"(pp)":[131],"test-set":[132],"accuracy":[133],"FLECC)":[135],"best":[138],"transformer-based":[139],"trans2feat":[140],"variants.":[141],"In":[142],"meanwhile,":[144],"remain":[149],"inspectable.":[150]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-20T00:00:00"}